End of training
Browse files- README.md +7 -17
- pytorch_model.bin +1 -1
- trainer_state.json +835 -935
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [alexue4/text-normalization-ru-new](https://huggingface.co/alexue4/text-normalization-ru-new) on the None dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 0.
|
| 19 |
- Mean Distance: 0
|
| 20 |
- Max Distance: 8
|
| 21 |
|
|
@@ -43,27 +43,17 @@ The following hyperparameters were used during training:
|
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
- lr_scheduler_warmup_ratio: 0.1
|
| 46 |
-
- num_epochs:
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss | Mean Distance | Max Distance |
|
| 51 |
|:-------------:|:-----:|:------:|:---------------:|:-------------:|:------------:|
|
| 52 |
-
| 0.
|
| 53 |
-
| 0.
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.0032 | 6.0 | 137496 | 0.0288 | 0 | 8 |
|
| 58 |
-
| 0.003 | 7.0 | 160412 | 0.0308 | 0 | 8 |
|
| 59 |
-
| 0.0025 | 8.0 | 183328 | 0.0305 | 0 | 8 |
|
| 60 |
-
| 0.0025 | 9.0 | 206244 | 0.0303 | 0 | 8 |
|
| 61 |
-
| 0.0023 | 10.0 | 229160 | 0.0341 | 0 | 8 |
|
| 62 |
-
| 0.0022 | 11.0 | 252076 | 0.0329 | 0 | 8 |
|
| 63 |
-
| 0.0019 | 12.0 | 274992 | 0.0336 | 0 | 8 |
|
| 64 |
-
| 0.002 | 13.0 | 297908 | 0.0358 | 0 | 8 |
|
| 65 |
-
| 0.0018 | 14.0 | 320824 | 0.0355 | 0 | 8 |
|
| 66 |
-
| 0.0019 | 15.0 | 343740 | 0.0366 | 0 | 8 |
|
| 67 |
|
| 68 |
|
| 69 |
### Framework versions
|
|
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [alexue4/text-normalization-ru-new](https://huggingface.co/alexue4/text-normalization-ru-new) on the None dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.0279
|
| 19 |
- Mean Distance: 0
|
| 20 |
- Max Distance: 8
|
| 21 |
|
|
|
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
- lr_scheduler_warmup_ratio: 0.1
|
| 46 |
+
- num_epochs: 5
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss | Mean Distance | Max Distance |
|
| 51 |
|:-------------:|:-----:|:------:|:---------------:|:-------------:|:------------:|
|
| 52 |
+
| 0.0024 | 1.0 | 22994 | 0.0264 | 0 | 8 |
|
| 53 |
+
| 0.0022 | 2.0 | 45988 | 0.0259 | 0 | 8 |
|
| 54 |
+
| 0.0019 | 3.0 | 68982 | 0.0292 | 0 | 8 |
|
| 55 |
+
| 0.0016 | 4.0 | 91976 | 0.0281 | 0 | 8 |
|
| 56 |
+
| 0.0016 | 5.0 | 114970 | 0.0279 | 0 | 8 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
|
| 58 |
|
| 59 |
### Framework versions
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 258643461
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02a57c7242c971b094f9debfa498d92a23843f114d3e18a09c850885d9c933eb
|
| 3 |
size 258643461
|
trainer_state.json
CHANGED
|
@@ -1,1378 +1,1278 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.0,
|
| 13 |
-
"learning_rate":
|
| 14 |
-
"loss": 0.
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch": 0.
|
| 19 |
-
"learning_rate": 5.
|
| 20 |
-
"loss": 0.
|
| 21 |
-
"step":
|
| 22 |
-
},
|
| 23 |
-
{
|
| 24 |
-
"epoch": 0.15,
|
| 25 |
-
"learning_rate": 1.0001745505323792e-05,
|
| 26 |
-
"loss": 0.0061,
|
| 27 |
-
"step": 3438
|
| 28 |
-
},
|
| 29 |
-
{
|
| 30 |
-
"epoch": 0.23,
|
| 31 |
-
"learning_rate": 1.5002618257985687e-05,
|
| 32 |
-
"loss": 0.0059,
|
| 33 |
-
"step": 5157
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
| 37 |
-
"learning_rate":
|
| 38 |
-
"loss": 0.
|
| 39 |
-
"step":
|
| 40 |
},
|
| 41 |
{
|
| 42 |
-
"epoch": 0.
|
| 43 |
-
"learning_rate":
|
| 44 |
-
"loss": 0.
|
| 45 |
-
"step":
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss": 0.
|
| 51 |
-
"step":
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"learning_rate":
|
| 56 |
-
"loss": 0.
|
| 57 |
-
"step":
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"epoch": 0.
|
| 61 |
-
"learning_rate":
|
| 62 |
-
"loss": 0.
|
| 63 |
-
"step":
|
| 64 |
},
|
| 65 |
{
|
| 66 |
-
"epoch": 0.
|
| 67 |
-
"learning_rate":
|
| 68 |
-
"loss": 0.
|
| 69 |
-
"step":
|
| 70 |
},
|
| 71 |
{
|
| 72 |
-
"epoch": 0.
|
| 73 |
-
"learning_rate":
|
| 74 |
-
"loss": 0.
|
| 75 |
-
"step":
|
| 76 |
},
|
| 77 |
{
|
| 78 |
-
"epoch": 0.
|
| 79 |
-
"learning_rate":
|
| 80 |
-
"loss": 0.
|
| 81 |
-
"step":
|
| 82 |
},
|
| 83 |
{
|
| 84 |
-
"epoch": 0.
|
| 85 |
-
"learning_rate":
|
| 86 |
-
"loss": 0.
|
| 87 |
-
"step":
|
| 88 |
},
|
| 89 |
{
|
| 90 |
-
"epoch": 0.
|
| 91 |
-
"learning_rate":
|
| 92 |
-
"loss": 0.
|
| 93 |
-
"step":
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch":
|
| 97 |
-
"
|
| 98 |
-
"
|
| 99 |
-
"
|
| 100 |
-
"eval_runtime": 14.4629,
|
| 101 |
-
"eval_samples_per_second": 17.355,
|
| 102 |
-
"eval_steps_per_second": 1.175,
|
| 103 |
-
"step": 22916
|
| 104 |
},
|
| 105 |
{
|
| 106 |
-
"epoch":
|
| 107 |
-
"learning_rate":
|
| 108 |
-
"loss": 0.
|
| 109 |
-
"step":
|
| 110 |
},
|
| 111 |
{
|
| 112 |
-
"epoch":
|
| 113 |
-
"learning_rate": 7.
|
| 114 |
-
"loss": 0.
|
| 115 |
-
"step":
|
| 116 |
},
|
| 117 |
{
|
| 118 |
-
"epoch":
|
| 119 |
-
"learning_rate":
|
| 120 |
-
"loss": 0.
|
| 121 |
-
"step":
|
| 122 |
},
|
| 123 |
{
|
| 124 |
-
"epoch":
|
| 125 |
-
"learning_rate": 8.
|
| 126 |
-
"loss": 0.
|
| 127 |
-
"step":
|
| 128 |
},
|
| 129 |
{
|
| 130 |
-
"epoch":
|
| 131 |
-
"learning_rate":
|
| 132 |
-
"loss": 0.
|
| 133 |
-
"step":
|
| 134 |
},
|
| 135 |
{
|
| 136 |
-
"epoch":
|
| 137 |
-
"learning_rate": 9.
|
| 138 |
-
"loss": 0.
|
| 139 |
-
"step":
|
| 140 |
},
|
| 141 |
{
|
| 142 |
-
"epoch":
|
| 143 |
-
"learning_rate": 9.
|
| 144 |
-
"loss": 0.
|
| 145 |
-
"step":
|
| 146 |
},
|
| 147 |
{
|
| 148 |
-
"epoch":
|
| 149 |
-
"learning_rate": 9.
|
| 150 |
-
"loss": 0.
|
| 151 |
-
"step":
|
| 152 |
},
|
| 153 |
{
|
| 154 |
-
"epoch":
|
| 155 |
-
"learning_rate": 9.
|
| 156 |
-
"loss": 0.
|
| 157 |
-
"step":
|
| 158 |
},
|
| 159 |
{
|
| 160 |
-
"epoch":
|
| 161 |
-
"learning_rate": 9.
|
| 162 |
-
"loss": 0.
|
| 163 |
-
"step":
|
| 164 |
},
|
| 165 |
{
|
| 166 |
-
"epoch":
|
| 167 |
-
"learning_rate": 9.
|
| 168 |
-
"loss": 0.
|
| 169 |
-
"step":
|
| 170 |
},
|
| 171 |
{
|
| 172 |
-
"epoch":
|
| 173 |
-
"learning_rate": 9.
|
| 174 |
-
"loss": 0.
|
| 175 |
-
"step":
|
| 176 |
},
|
| 177 |
{
|
| 178 |
-
"epoch":
|
| 179 |
-
"learning_rate": 9.
|
| 180 |
-
"loss": 0.
|
| 181 |
-
"step":
|
| 182 |
},
|
| 183 |
{
|
| 184 |
-
"epoch":
|
| 185 |
-
"
|
| 186 |
-
"
|
| 187 |
-
"
|
| 188 |
-
"eval_runtime": 13.5883,
|
| 189 |
-
"eval_samples_per_second": 18.472,
|
| 190 |
-
"eval_steps_per_second": 1.251,
|
| 191 |
-
"step": 45832
|
| 192 |
},
|
| 193 |
{
|
| 194 |
-
"epoch":
|
| 195 |
-
"learning_rate": 9.
|
| 196 |
-
"loss": 0.
|
| 197 |
-
"step":
|
| 198 |
},
|
| 199 |
{
|
| 200 |
-
"epoch":
|
| 201 |
-
"learning_rate": 9.
|
| 202 |
-
"loss": 0.
|
| 203 |
-
"step":
|
| 204 |
},
|
| 205 |
{
|
| 206 |
-
"epoch":
|
| 207 |
-
"learning_rate": 9.
|
| 208 |
-
"loss": 0.
|
| 209 |
-
"step":
|
| 210 |
},
|
| 211 |
{
|
| 212 |
-
"epoch":
|
| 213 |
-
"learning_rate": 9.
|
| 214 |
-
"loss": 0.
|
| 215 |
-
"step":
|
| 216 |
},
|
| 217 |
{
|
| 218 |
-
"epoch":
|
| 219 |
-
"learning_rate": 9.
|
| 220 |
-
"loss": 0.
|
| 221 |
-
"step":
|
| 222 |
},
|
| 223 |
{
|
| 224 |
-
"epoch":
|
| 225 |
-
"learning_rate": 9.
|
| 226 |
-
"loss": 0.
|
| 227 |
-
"step":
|
| 228 |
},
|
| 229 |
{
|
| 230 |
-
"epoch":
|
| 231 |
-
"learning_rate": 9.
|
| 232 |
-
"loss": 0.
|
| 233 |
-
"step":
|
| 234 |
},
|
| 235 |
{
|
| 236 |
-
"epoch":
|
| 237 |
-
"learning_rate": 9.
|
| 238 |
-
"loss": 0.
|
| 239 |
-
"step":
|
| 240 |
},
|
| 241 |
{
|
| 242 |
-
"epoch":
|
| 243 |
-
"learning_rate": 9.
|
| 244 |
-
"loss": 0.
|
| 245 |
-
"step":
|
| 246 |
},
|
| 247 |
{
|
| 248 |
-
"epoch":
|
| 249 |
-
"learning_rate": 9.
|
| 250 |
-
"loss": 0.
|
| 251 |
-
"step":
|
| 252 |
},
|
| 253 |
{
|
| 254 |
-
"epoch":
|
| 255 |
-
"learning_rate": 9.
|
| 256 |
-
"loss": 0.
|
| 257 |
-
"step":
|
| 258 |
},
|
| 259 |
{
|
| 260 |
-
"epoch":
|
| 261 |
-
"learning_rate": 8.
|
| 262 |
-
"loss": 0.
|
| 263 |
-
"step":
|
| 264 |
},
|
| 265 |
{
|
| 266 |
-
"epoch":
|
| 267 |
-
"learning_rate": 8.
|
| 268 |
-
"loss": 0.
|
| 269 |
-
"step":
|
| 270 |
},
|
| 271 |
{
|
| 272 |
-
"epoch":
|
| 273 |
-
"eval_loss": 0.
|
| 274 |
"eval_max_distance": 8,
|
| 275 |
"eval_mean_distance": 0,
|
| 276 |
-
"eval_runtime":
|
| 277 |
-
"eval_samples_per_second":
|
| 278 |
-
"eval_steps_per_second":
|
| 279 |
-
"step":
|
| 280 |
-
},
|
| 281 |
-
{
|
| 282 |
-
"epoch": 3.0,
|
| 283 |
-
"learning_rate": 8.888500998816935e-05,
|
| 284 |
-
"loss": 0.0046,
|
| 285 |
-
"step": 68760
|
| 286 |
},
|
| 287 |
{
|
| 288 |
-
"epoch":
|
| 289 |
-
"learning_rate": 8.
|
| 290 |
-
"loss": 0.
|
| 291 |
-
"step":
|
| 292 |
-
},
|
| 293 |
-
{
|
| 294 |
-
"epoch": 3.15,
|
| 295 |
-
"learning_rate": 8.777370493202228e-05,
|
| 296 |
-
"loss": 0.0036,
|
| 297 |
-
"step": 72198
|
| 298 |
},
|
| 299 |
{
|
| 300 |
-
"epoch":
|
| 301 |
-
"learning_rate": 8.
|
| 302 |
-
"loss": 0.
|
| 303 |
-
"step":
|
| 304 |
},
|
| 305 |
{
|
| 306 |
-
"epoch":
|
| 307 |
-
"learning_rate": 8.
|
| 308 |
-
"loss": 0.
|
| 309 |
-
"step":
|
| 310 |
},
|
| 311 |
{
|
| 312 |
-
"epoch":
|
| 313 |
-
"learning_rate": 8.
|
| 314 |
-
"loss": 0.
|
| 315 |
-
"step":
|
| 316 |
},
|
| 317 |
{
|
| 318 |
-
"epoch":
|
| 319 |
-
"learning_rate": 8.
|
| 320 |
-
"loss": 0.
|
| 321 |
-
"step":
|
| 322 |
},
|
| 323 |
{
|
| 324 |
-
"epoch":
|
| 325 |
-
"learning_rate": 8.
|
| 326 |
-
"loss": 0.
|
| 327 |
-
"step":
|
| 328 |
},
|
| 329 |
{
|
| 330 |
-
"epoch":
|
| 331 |
-
"learning_rate": 8.
|
| 332 |
-
"loss": 0.
|
| 333 |
-
"step":
|
| 334 |
},
|
| 335 |
{
|
| 336 |
-
"epoch":
|
| 337 |
-
"learning_rate": 8.
|
| 338 |
-
"loss": 0.
|
| 339 |
-
"step":
|
| 340 |
},
|
| 341 |
{
|
| 342 |
-
"epoch":
|
| 343 |
-
"learning_rate": 8.
|
| 344 |
-
"loss": 0.
|
| 345 |
-
"step":
|
| 346 |
},
|
| 347 |
{
|
| 348 |
-
"epoch":
|
| 349 |
-
"learning_rate": 8.
|
| 350 |
-
"loss": 0.
|
| 351 |
-
"step":
|
| 352 |
},
|
| 353 |
{
|
| 354 |
-
"epoch":
|
| 355 |
-
"learning_rate": 8.
|
| 356 |
-
"loss": 0.
|
| 357 |
-
"step":
|
| 358 |
},
|
| 359 |
{
|
| 360 |
-
"epoch":
|
| 361 |
-
"learning_rate": 8.
|
| 362 |
-
"loss": 0.
|
| 363 |
-
"step":
|
| 364 |
},
|
| 365 |
{
|
| 366 |
-
"epoch":
|
| 367 |
-
"
|
| 368 |
-
"
|
| 369 |
-
"
|
| 370 |
-
"eval_runtime": 13.351,
|
| 371 |
-
"eval_samples_per_second": 18.8,
|
| 372 |
-
"eval_steps_per_second": 1.273,
|
| 373 |
-
"step": 91664
|
| 374 |
},
|
| 375 |
{
|
| 376 |
-
"epoch":
|
| 377 |
-
"learning_rate": 8.
|
| 378 |
-
"loss": 0.
|
| 379 |
-
"step":
|
| 380 |
},
|
| 381 |
{
|
| 382 |
-
"epoch":
|
| 383 |
-
"learning_rate": 8.
|
| 384 |
-
"loss": 0.
|
| 385 |
-
"step":
|
| 386 |
},
|
| 387 |
{
|
| 388 |
-
"epoch":
|
| 389 |
-
"learning_rate":
|
| 390 |
-
"loss": 0.
|
| 391 |
-
"step":
|
| 392 |
},
|
| 393 |
{
|
| 394 |
-
"epoch": 4
|
| 395 |
-
"learning_rate": 7.
|
| 396 |
-
"loss": 0.
|
| 397 |
-
"step":
|
| 398 |
},
|
| 399 |
{
|
| 400 |
-
"epoch":
|
| 401 |
-
"learning_rate": 7.
|
| 402 |
-
"loss": 0.
|
| 403 |
-
"step":
|
| 404 |
},
|
| 405 |
{
|
| 406 |
-
"epoch":
|
| 407 |
-
"learning_rate": 7.
|
| 408 |
-
"loss": 0.
|
| 409 |
-
"step":
|
| 410 |
},
|
| 411 |
{
|
| 412 |
-
"epoch":
|
| 413 |
-
"learning_rate": 7.
|
| 414 |
-
"loss": 0.
|
| 415 |
-
"step":
|
| 416 |
},
|
| 417 |
{
|
| 418 |
-
"epoch":
|
| 419 |
-
"learning_rate": 7.
|
| 420 |
-
"loss": 0.
|
| 421 |
-
"step":
|
| 422 |
},
|
| 423 |
{
|
| 424 |
-
"epoch":
|
| 425 |
-
"learning_rate": 7.
|
| 426 |
-
"loss": 0.
|
| 427 |
-
"step":
|
| 428 |
},
|
| 429 |
{
|
| 430 |
-
"epoch":
|
| 431 |
-
"learning_rate": 7.
|
| 432 |
-
"loss": 0.
|
| 433 |
-
"step":
|
| 434 |
},
|
| 435 |
{
|
| 436 |
-
"epoch":
|
| 437 |
-
"learning_rate": 7.
|
| 438 |
-
"loss": 0.
|
| 439 |
-
"step":
|
| 440 |
},
|
| 441 |
{
|
| 442 |
-
"epoch":
|
| 443 |
-
"learning_rate": 7.
|
| 444 |
-
"loss": 0.
|
| 445 |
-
"step":
|
| 446 |
},
|
| 447 |
{
|
| 448 |
-
"epoch":
|
| 449 |
-
"learning_rate": 7.
|
| 450 |
-
"loss": 0.
|
| 451 |
-
"step":
|
| 452 |
},
|
| 453 |
{
|
| 454 |
-
"epoch":
|
| 455 |
-
"
|
| 456 |
-
"
|
| 457 |
-
"
|
| 458 |
-
"eval_runtime": 13.4584,
|
| 459 |
-
"eval_samples_per_second": 18.65,
|
| 460 |
-
"eval_steps_per_second": 1.263,
|
| 461 |
-
"step": 114580
|
| 462 |
},
|
| 463 |
{
|
| 464 |
-
"epoch":
|
| 465 |
-
"learning_rate": 7.
|
| 466 |
-
"loss": 0.
|
| 467 |
-
"step":
|
| 468 |
},
|
| 469 |
{
|
| 470 |
-
"epoch":
|
| 471 |
-
"learning_rate": 7.
|
| 472 |
-
"loss": 0.
|
| 473 |
-
"step":
|
| 474 |
},
|
| 475 |
{
|
| 476 |
-
"epoch":
|
| 477 |
-
"learning_rate": 7.
|
| 478 |
-
"loss": 0.
|
| 479 |
-
"step":
|
| 480 |
},
|
| 481 |
{
|
| 482 |
-
"epoch":
|
| 483 |
-
"learning_rate": 7.
|
| 484 |
-
"loss": 0.
|
| 485 |
-
"step":
|
| 486 |
},
|
| 487 |
{
|
| 488 |
-
"epoch":
|
| 489 |
-
"learning_rate": 7.
|
| 490 |
-
"loss": 0.
|
| 491 |
-
"step":
|
| 492 |
},
|
| 493 |
{
|
| 494 |
-
"epoch":
|
| 495 |
-
"learning_rate": 7.
|
| 496 |
-
"loss": 0.
|
| 497 |
-
"step":
|
| 498 |
},
|
| 499 |
{
|
| 500 |
-
"epoch":
|
| 501 |
-
"learning_rate": 7.
|
| 502 |
-
"loss": 0.
|
| 503 |
-
"step":
|
| 504 |
},
|
| 505 |
{
|
| 506 |
-
"epoch":
|
| 507 |
-
"learning_rate": 6.
|
| 508 |
-
"loss": 0.
|
| 509 |
-
"step":
|
| 510 |
},
|
| 511 |
{
|
| 512 |
-
"epoch":
|
| 513 |
-
"learning_rate": 6.
|
| 514 |
-
"loss": 0.
|
| 515 |
-
"step":
|
| 516 |
},
|
| 517 |
{
|
| 518 |
-
"epoch":
|
| 519 |
-
"learning_rate": 6.
|
| 520 |
-
"loss": 0.
|
| 521 |
-
"step":
|
| 522 |
},
|
| 523 |
{
|
| 524 |
-
"epoch":
|
| 525 |
-
"learning_rate": 6.
|
| 526 |
-
"loss": 0.
|
| 527 |
-
"step":
|
| 528 |
},
|
| 529 |
{
|
| 530 |
-
"epoch":
|
| 531 |
-
"learning_rate": 6.
|
| 532 |
-
"loss": 0.
|
| 533 |
-
"step":
|
| 534 |
},
|
| 535 |
{
|
| 536 |
-
"epoch":
|
| 537 |
-
"learning_rate": 6.
|
| 538 |
-
"loss": 0.
|
| 539 |
-
"step":
|
| 540 |
},
|
| 541 |
{
|
| 542 |
-
"epoch":
|
| 543 |
-
"eval_loss": 0.
|
| 544 |
"eval_max_distance": 8,
|
| 545 |
"eval_mean_distance": 0,
|
| 546 |
-
"eval_runtime":
|
| 547 |
-
"eval_samples_per_second":
|
| 548 |
-
"eval_steps_per_second":
|
| 549 |
-
"step":
|
| 550 |
-
},
|
| 551 |
-
{
|
| 552 |
-
"epoch": 6.0,
|
| 553 |
-
"learning_rate": 6.66589088652276e-05,
|
| 554 |
-
"loss": 0.0033,
|
| 555 |
-
"step": 137520
|
| 556 |
-
},
|
| 557 |
-
{
|
| 558 |
-
"epoch": 6.08,
|
| 559 |
-
"learning_rate": 6.610325633715405e-05,
|
| 560 |
-
"loss": 0.0028,
|
| 561 |
-
"step": 139239
|
| 562 |
},
|
| 563 |
{
|
| 564 |
-
"epoch":
|
| 565 |
-
"learning_rate": 6.
|
| 566 |
-
"loss": 0.
|
| 567 |
-
"step":
|
| 568 |
},
|
| 569 |
{
|
| 570 |
-
"epoch":
|
| 571 |
-
"learning_rate": 6.
|
| 572 |
-
"loss": 0.
|
| 573 |
-
"step":
|
| 574 |
},
|
| 575 |
{
|
| 576 |
-
"epoch":
|
| 577 |
-
"learning_rate": 6.
|
| 578 |
-
"loss": 0.
|
| 579 |
-
"step":
|
| 580 |
},
|
| 581 |
{
|
| 582 |
-
"epoch":
|
| 583 |
-
"learning_rate": 6.
|
| 584 |
-
"loss": 0.
|
| 585 |
-
"step":
|
| 586 |
},
|
| 587 |
{
|
| 588 |
-
"epoch":
|
| 589 |
-
"learning_rate": 6.
|
| 590 |
-
"loss": 0.
|
| 591 |
-
"step":
|
| 592 |
},
|
| 593 |
{
|
| 594 |
-
"epoch":
|
| 595 |
-
"learning_rate": 6.
|
| 596 |
-
"loss": 0.
|
| 597 |
-
"step":
|
| 598 |
},
|
| 599 |
{
|
| 600 |
-
"epoch":
|
| 601 |
-
"learning_rate": 6.
|
| 602 |
-
"loss": 0.
|
| 603 |
-
"step":
|
| 604 |
},
|
| 605 |
{
|
| 606 |
-
"epoch":
|
| 607 |
-
"learning_rate": 6.
|
| 608 |
-
"loss": 0.
|
| 609 |
-
"step":
|
| 610 |
},
|
| 611 |
{
|
| 612 |
-
"epoch":
|
| 613 |
-
"learning_rate": 6.
|
| 614 |
-
"loss": 0.
|
| 615 |
-
"step":
|
| 616 |
},
|
| 617 |
{
|
| 618 |
-
"epoch":
|
| 619 |
-
"learning_rate": 6.
|
| 620 |
-
"loss": 0.
|
| 621 |
-
"step":
|
| 622 |
},
|
| 623 |
{
|
| 624 |
-
"epoch":
|
| 625 |
-
"learning_rate":
|
| 626 |
-
"loss": 0.
|
| 627 |
-
"step":
|
| 628 |
},
|
| 629 |
{
|
| 630 |
-
"epoch":
|
| 631 |
-
"learning_rate":
|
| 632 |
-
"loss": 0.
|
| 633 |
-
"step":
|
| 634 |
},
|
| 635 |
{
|
| 636 |
-
"epoch":
|
| 637 |
-
"
|
| 638 |
-
"
|
| 639 |
-
"
|
| 640 |
-
"eval_runtime": 13.4895,
|
| 641 |
-
"eval_samples_per_second": 18.607,
|
| 642 |
-
"eval_steps_per_second": 1.26,
|
| 643 |
-
"step": 160412
|
| 644 |
},
|
| 645 |
{
|
| 646 |
-
"epoch":
|
| 647 |
-
"learning_rate": 5.
|
| 648 |
-
"loss": 0.
|
| 649 |
-
"step":
|
| 650 |
},
|
| 651 |
{
|
| 652 |
-
"epoch":
|
| 653 |
-
"learning_rate": 5.
|
| 654 |
-
"loss": 0.
|
| 655 |
-
"step":
|
| 656 |
},
|
| 657 |
{
|
| 658 |
-
"epoch":
|
| 659 |
-
"learning_rate": 5.
|
| 660 |
-
"loss": 0.
|
| 661 |
-
"step":
|
| 662 |
},
|
| 663 |
{
|
| 664 |
-
"epoch":
|
| 665 |
-
"learning_rate": 5.
|
| 666 |
-
"loss": 0.
|
| 667 |
-
"step":
|
| 668 |
},
|
| 669 |
{
|
| 670 |
-
"epoch":
|
| 671 |
-
"learning_rate": 5.
|
| 672 |
-
"loss": 0.
|
| 673 |
-
"step":
|
| 674 |
},
|
| 675 |
{
|
| 676 |
-
"epoch":
|
| 677 |
-
"learning_rate": 5.
|
| 678 |
-
"loss": 0.
|
| 679 |
-
"step":
|
| 680 |
},
|
| 681 |
{
|
| 682 |
-
"epoch":
|
| 683 |
-
"learning_rate": 5.
|
| 684 |
-
"loss": 0.
|
| 685 |
-
"step":
|
| 686 |
},
|
| 687 |
{
|
| 688 |
-
"epoch":
|
| 689 |
-
"learning_rate": 5.
|
| 690 |
-
"loss": 0.
|
| 691 |
-
"step":
|
| 692 |
},
|
| 693 |
{
|
| 694 |
-
"epoch":
|
| 695 |
-
"learning_rate": 5.
|
| 696 |
-
"loss": 0.
|
| 697 |
-
"step":
|
| 698 |
},
|
| 699 |
{
|
| 700 |
-
"epoch":
|
| 701 |
-
"learning_rate": 5.
|
| 702 |
-
"loss": 0.
|
| 703 |
-
"step":
|
| 704 |
},
|
| 705 |
{
|
| 706 |
-
"epoch":
|
| 707 |
-
"learning_rate": 5.
|
| 708 |
-
"loss": 0.
|
| 709 |
-
"step":
|
| 710 |
},
|
| 711 |
{
|
| 712 |
-
"epoch":
|
| 713 |
-
"learning_rate": 5.
|
| 714 |
-
"loss": 0.
|
| 715 |
-
"step":
|
| 716 |
},
|
| 717 |
{
|
| 718 |
-
"epoch":
|
| 719 |
-
"learning_rate": 5.
|
| 720 |
-
"loss": 0.
|
| 721 |
-
"step":
|
| 722 |
},
|
| 723 |
{
|
| 724 |
-
"epoch":
|
| 725 |
-
"
|
| 726 |
-
"
|
| 727 |
-
"
|
| 728 |
-
"eval_runtime": 13.5077,
|
| 729 |
-
"eval_samples_per_second": 18.582,
|
| 730 |
-
"eval_steps_per_second": 1.259,
|
| 731 |
-
"step": 183328
|
| 732 |
},
|
| 733 |
{
|
| 734 |
-
"epoch":
|
| 735 |
-
"learning_rate": 5.
|
| 736 |
-
"loss": 0.
|
| 737 |
-
"step":
|
| 738 |
},
|
| 739 |
{
|
| 740 |
-
"epoch":
|
| 741 |
-
"learning_rate": 5.
|
| 742 |
-
"loss": 0.
|
| 743 |
-
"step":
|
| 744 |
},
|
| 745 |
{
|
| 746 |
-
"epoch":
|
| 747 |
-
"learning_rate": 5.
|
| 748 |
-
"loss": 0.
|
| 749 |
-
"step":
|
| 750 |
},
|
| 751 |
{
|
| 752 |
-
"epoch":
|
| 753 |
-
"learning_rate": 4.
|
| 754 |
-
"loss": 0.
|
| 755 |
-
"step":
|
| 756 |
},
|
| 757 |
{
|
| 758 |
-
"epoch":
|
| 759 |
-
"learning_rate": 4.
|
| 760 |
-
"loss": 0.
|
| 761 |
-
"step":
|
| 762 |
},
|
| 763 |
{
|
| 764 |
-
"epoch": 8
|
| 765 |
-
"learning_rate": 4.
|
| 766 |
-
"loss": 0.
|
| 767 |
-
"step":
|
| 768 |
},
|
| 769 |
{
|
| 770 |
-
"epoch":
|
| 771 |
-
"learning_rate": 4.
|
| 772 |
-
"loss": 0.
|
| 773 |
-
"step":
|
| 774 |
},
|
| 775 |
{
|
| 776 |
-
"epoch":
|
| 777 |
-
"learning_rate": 4.
|
| 778 |
-
"loss": 0.
|
| 779 |
-
"step":
|
| 780 |
},
|
| 781 |
{
|
| 782 |
-
"epoch":
|
| 783 |
-
"learning_rate": 4.
|
| 784 |
-
"loss": 0.
|
| 785 |
-
"step":
|
| 786 |
},
|
| 787 |
{
|
| 788 |
-
"epoch":
|
| 789 |
-
"learning_rate": 4.
|
| 790 |
-
"loss": 0.
|
| 791 |
-
"step":
|
| 792 |
},
|
| 793 |
{
|
| 794 |
-
"epoch":
|
| 795 |
-
"learning_rate": 4.
|
| 796 |
-
"loss": 0.
|
| 797 |
-
"step":
|
| 798 |
},
|
| 799 |
{
|
| 800 |
-
"epoch":
|
| 801 |
-
"learning_rate": 4.
|
| 802 |
-
"loss": 0.
|
| 803 |
-
"step":
|
| 804 |
},
|
| 805 |
{
|
| 806 |
-
"epoch":
|
| 807 |
-
"learning_rate": 4.
|
| 808 |
-
"loss": 0.
|
| 809 |
-
"step":
|
| 810 |
},
|
| 811 |
{
|
| 812 |
-
"epoch":
|
| 813 |
-
"eval_loss": 0.
|
| 814 |
"eval_max_distance": 8,
|
| 815 |
"eval_mean_distance": 0,
|
| 816 |
-
"eval_runtime":
|
| 817 |
-
"eval_samples_per_second":
|
| 818 |
-
"eval_steps_per_second":
|
| 819 |
-
"step":
|
| 820 |
},
|
| 821 |
{
|
| 822 |
-
"epoch":
|
| 823 |
-
"learning_rate": 4.
|
| 824 |
-
"loss": 0.0026,
|
| 825 |
-
"step": 206280
|
| 826 |
-
},
|
| 827 |
-
{
|
| 828 |
-
"epoch": 9.08,
|
| 829 |
-
"learning_rate": 4.38771552142123e-05,
|
| 830 |
"loss": 0.0021,
|
| 831 |
-
"step":
|
| 832 |
},
|
| 833 |
{
|
| 834 |
-
"epoch":
|
| 835 |
-
"learning_rate": 4.
|
| 836 |
-
"loss": 0.
|
| 837 |
-
"step":
|
| 838 |
-
},
|
| 839 |
-
{
|
| 840 |
-
"epoch": 9.23,
|
| 841 |
-
"learning_rate": 4.2765850158065204e-05,
|
| 842 |
-
"loss": 0.0022,
|
| 843 |
-
"step": 211437
|
| 844 |
-
},
|
| 845 |
-
{
|
| 846 |
-
"epoch": 9.3,
|
| 847 |
-
"learning_rate": 4.221019762999166e-05,
|
| 848 |
-
"loss": 0.0023,
|
| 849 |
-
"step": 213156
|
| 850 |
},
|
| 851 |
{
|
| 852 |
-
"epoch":
|
| 853 |
-
"learning_rate": 4.
|
| 854 |
-
"loss": 0.
|
| 855 |
-
"step":
|
| 856 |
},
|
| 857 |
{
|
| 858 |
-
"epoch":
|
| 859 |
-
"learning_rate": 4.
|
| 860 |
-
"loss": 0.
|
| 861 |
-
"step":
|
| 862 |
},
|
| 863 |
{
|
| 864 |
-
"epoch":
|
| 865 |
-
"learning_rate": 4.
|
| 866 |
-
"loss": 0.
|
| 867 |
-
"step":
|
| 868 |
},
|
| 869 |
{
|
| 870 |
-
"epoch":
|
| 871 |
-
"learning_rate":
|
| 872 |
-
"loss": 0.
|
| 873 |
-
"step":
|
| 874 |
},
|
| 875 |
{
|
| 876 |
-
"epoch":
|
| 877 |
-
"learning_rate":
|
| 878 |
-
"loss": 0.
|
| 879 |
-
"step":
|
| 880 |
},
|
| 881 |
{
|
| 882 |
-
"epoch":
|
| 883 |
-
"learning_rate":
|
| 884 |
-
"loss": 0.
|
| 885 |
-
"step":
|
| 886 |
},
|
| 887 |
{
|
| 888 |
-
"epoch":
|
| 889 |
-
"learning_rate": 3.
|
| 890 |
-
"loss": 0.
|
| 891 |
-
"step":
|
| 892 |
},
|
| 893 |
{
|
| 894 |
-
"epoch":
|
| 895 |
-
"learning_rate": 3.
|
| 896 |
-
"loss": 0.
|
| 897 |
-
"step":
|
| 898 |
},
|
| 899 |
{
|
| 900 |
-
"epoch":
|
| 901 |
-
"learning_rate": 3.
|
| 902 |
-
"loss": 0.
|
| 903 |
-
"step":
|
| 904 |
},
|
| 905 |
{
|
| 906 |
-
"epoch":
|
| 907 |
-
"
|
| 908 |
-
"
|
| 909 |
-
"
|
| 910 |
-
"eval_runtime": 13.4726,
|
| 911 |
-
"eval_samples_per_second": 18.63,
|
| 912 |
-
"eval_steps_per_second": 1.262,
|
| 913 |
-
"step": 229160
|
| 914 |
},
|
| 915 |
{
|
| 916 |
-
"epoch":
|
| 917 |
-
"learning_rate": 3.
|
| 918 |
-
"loss": 0.
|
| 919 |
-
"step":
|
| 920 |
},
|
| 921 |
{
|
| 922 |
-
"epoch":
|
| 923 |
-
"learning_rate": 3.
|
| 924 |
-
"loss": 0.
|
| 925 |
-
"step":
|
| 926 |
},
|
| 927 |
{
|
| 928 |
-
"epoch":
|
| 929 |
-
"learning_rate": 3.
|
| 930 |
-
"loss": 0.
|
| 931 |
-
"step":
|
| 932 |
},
|
| 933 |
{
|
| 934 |
-
"epoch":
|
| 935 |
-
"learning_rate": 3.
|
| 936 |
-
"loss": 0.
|
| 937 |
-
"step":
|
| 938 |
},
|
| 939 |
{
|
| 940 |
-
"epoch":
|
| 941 |
-
"learning_rate": 3.
|
| 942 |
-
"loss": 0.
|
| 943 |
-
"step":
|
| 944 |
},
|
| 945 |
{
|
| 946 |
-
"epoch":
|
| 947 |
-
"learning_rate": 3.
|
| 948 |
-
"loss": 0.
|
| 949 |
-
"step":
|
| 950 |
},
|
| 951 |
{
|
| 952 |
-
"epoch":
|
| 953 |
-
"learning_rate": 3.
|
| 954 |
-
"loss": 0.
|
| 955 |
-
"step":
|
| 956 |
},
|
| 957 |
{
|
| 958 |
-
"epoch":
|
| 959 |
-
"learning_rate": 3.
|
| 960 |
-
"loss": 0.
|
| 961 |
-
"step":
|
| 962 |
},
|
| 963 |
{
|
| 964 |
-
"epoch":
|
| 965 |
-
"learning_rate": 3.
|
| 966 |
-
"loss": 0.
|
| 967 |
-
"step":
|
| 968 |
},
|
| 969 |
{
|
| 970 |
-
"epoch":
|
| 971 |
-
"learning_rate": 3.
|
| 972 |
-
"loss": 0.
|
| 973 |
-
"step":
|
| 974 |
},
|
| 975 |
{
|
| 976 |
-
"epoch":
|
| 977 |
-
"learning_rate": 3.
|
| 978 |
-
"loss": 0.
|
| 979 |
-
"step":
|
| 980 |
},
|
| 981 |
{
|
| 982 |
-
"epoch":
|
| 983 |
-
"learning_rate": 3.
|
| 984 |
"loss": 0.002,
|
| 985 |
-
"step":
|
| 986 |
},
|
| 987 |
{
|
| 988 |
-
"epoch":
|
| 989 |
-
"learning_rate":
|
| 990 |
-
"loss": 0.
|
| 991 |
-
"step":
|
| 992 |
},
|
| 993 |
{
|
| 994 |
-
"epoch":
|
| 995 |
-
"
|
| 996 |
-
"
|
| 997 |
-
"
|
| 998 |
-
"eval_runtime": 13.3832,
|
| 999 |
-
"eval_samples_per_second": 18.755,
|
| 1000 |
-
"eval_steps_per_second": 1.27,
|
| 1001 |
-
"step": 252076
|
| 1002 |
},
|
| 1003 |
{
|
| 1004 |
-
"epoch":
|
| 1005 |
-
"learning_rate": 2.
|
| 1006 |
-
"loss": 0.
|
| 1007 |
-
"step":
|
| 1008 |
},
|
| 1009 |
{
|
| 1010 |
-
"epoch":
|
| 1011 |
-
"learning_rate": 2.
|
| 1012 |
-
"loss": 0.
|
| 1013 |
-
"step":
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
-
"epoch":
|
| 1017 |
-
"learning_rate": 2.
|
| 1018 |
-
"loss": 0.
|
| 1019 |
-
"step":
|
| 1020 |
},
|
| 1021 |
{
|
| 1022 |
-
"epoch":
|
| 1023 |
-
"learning_rate": 2.
|
| 1024 |
-
"loss": 0.
|
| 1025 |
-
"step":
|
| 1026 |
},
|
| 1027 |
{
|
| 1028 |
-
"epoch":
|
| 1029 |
-
"learning_rate": 2.
|
| 1030 |
-
"loss": 0.
|
| 1031 |
-
"step":
|
| 1032 |
},
|
| 1033 |
{
|
| 1034 |
-
"epoch":
|
| 1035 |
-
"learning_rate": 2.
|
| 1036 |
"loss": 0.0019,
|
| 1037 |
-
"step":
|
| 1038 |
},
|
| 1039 |
{
|
| 1040 |
-
"epoch":
|
| 1041 |
-
"learning_rate": 2.
|
| 1042 |
"loss": 0.002,
|
| 1043 |
-
"step":
|
| 1044 |
},
|
| 1045 |
{
|
| 1046 |
-
"epoch":
|
| 1047 |
-
"learning_rate": 2.
|
| 1048 |
-
"loss": 0.
|
| 1049 |
-
"step":
|
| 1050 |
},
|
| 1051 |
{
|
| 1052 |
-
"epoch":
|
| 1053 |
-
"learning_rate": 2.
|
| 1054 |
-
"loss": 0.
|
| 1055 |
-
"step":
|
| 1056 |
},
|
| 1057 |
{
|
| 1058 |
-
"epoch":
|
| 1059 |
-
"learning_rate": 2.
|
| 1060 |
-
"loss": 0.
|
| 1061 |
-
"step":
|
| 1062 |
},
|
| 1063 |
{
|
| 1064 |
-
"epoch":
|
| 1065 |
-
"learning_rate": 2.
|
| 1066 |
-
"loss": 0.
|
| 1067 |
-
"step":
|
| 1068 |
},
|
| 1069 |
{
|
| 1070 |
-
"epoch":
|
| 1071 |
-
"learning_rate": 2.
|
| 1072 |
-
"loss": 0.
|
| 1073 |
-
"step":
|
| 1074 |
},
|
| 1075 |
{
|
| 1076 |
-
"epoch":
|
| 1077 |
-
"learning_rate": 2.
|
| 1078 |
"loss": 0.0019,
|
| 1079 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1080 |
},
|
| 1081 |
{
|
| 1082 |
-
"epoch":
|
| 1083 |
-
"eval_loss": 0.
|
| 1084 |
"eval_max_distance": 8,
|
| 1085 |
"eval_mean_distance": 0,
|
| 1086 |
-
"eval_runtime":
|
| 1087 |
-
"eval_samples_per_second":
|
| 1088 |
-
"eval_steps_per_second":
|
| 1089 |
-
"step":
|
| 1090 |
},
|
| 1091 |
{
|
| 1092 |
-
"epoch":
|
| 1093 |
-
"learning_rate": 2.
|
| 1094 |
-
"loss": 0.
|
| 1095 |
-
"step":
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
-
"epoch":
|
| 1099 |
-
"learning_rate": 2.
|
| 1100 |
-
"loss": 0.
|
| 1101 |
-
"step":
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
-
"epoch":
|
| 1105 |
-
"learning_rate": 2.
|
| 1106 |
-
"loss": 0.
|
| 1107 |
-
"step":
|
| 1108 |
},
|
| 1109 |
{
|
| 1110 |
-
"epoch":
|
| 1111 |
-
"learning_rate": 2.
|
| 1112 |
-
"loss": 0.
|
| 1113 |
-
"step":
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
-
"epoch":
|
| 1117 |
-
"learning_rate": 1.
|
| 1118 |
-
"loss": 0.
|
| 1119 |
-
"step":
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
-
"epoch":
|
| 1123 |
-
"learning_rate": 1.
|
| 1124 |
-
"loss": 0.
|
| 1125 |
-
"step":
|
| 1126 |
},
|
| 1127 |
{
|
| 1128 |
-
"epoch":
|
| 1129 |
-
"learning_rate": 1.
|
| 1130 |
-
"loss": 0.
|
| 1131 |
-
"step":
|
| 1132 |
},
|
| 1133 |
{
|
| 1134 |
-
"epoch":
|
| 1135 |
-
"learning_rate": 1.
|
| 1136 |
-
"loss": 0.
|
| 1137 |
-
"step":
|
| 1138 |
},
|
| 1139 |
{
|
| 1140 |
-
"epoch":
|
| 1141 |
-
"learning_rate": 1.
|
| 1142 |
-
"loss": 0.
|
| 1143 |
-
"step":
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
-
"epoch":
|
| 1147 |
-
"learning_rate": 1.
|
| 1148 |
-
"loss": 0.
|
| 1149 |
-
"step":
|
| 1150 |
},
|
| 1151 |
{
|
| 1152 |
-
"epoch":
|
| 1153 |
-
"learning_rate": 1.
|
| 1154 |
-
"loss": 0.
|
| 1155 |
-
"step":
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
-
"epoch":
|
| 1159 |
-
"learning_rate": 1.
|
| 1160 |
-
"loss": 0.
|
| 1161 |
-
"step":
|
| 1162 |
},
|
| 1163 |
{
|
| 1164 |
-
"epoch":
|
| 1165 |
-
"learning_rate": 1.
|
| 1166 |
-
"loss": 0.
|
| 1167 |
-
"step":
|
| 1168 |
},
|
| 1169 |
{
|
| 1170 |
-
"epoch":
|
| 1171 |
-
"learning_rate": 1.
|
| 1172 |
-
"loss": 0.
|
| 1173 |
-
"step":
|
| 1174 |
},
|
| 1175 |
{
|
| 1176 |
-
"epoch":
|
| 1177 |
-
"
|
| 1178 |
-
"
|
| 1179 |
-
"
|
| 1180 |
-
"eval_runtime": 13.4958,
|
| 1181 |
-
"eval_samples_per_second": 18.598,
|
| 1182 |
-
"eval_steps_per_second": 1.26,
|
| 1183 |
-
"step": 297908
|
| 1184 |
},
|
| 1185 |
{
|
| 1186 |
-
"epoch":
|
| 1187 |
-
"learning_rate": 1.
|
| 1188 |
"loss": 0.0019,
|
| 1189 |
-
"step":
|
| 1190 |
-
},
|
| 1191 |
-
{
|
| 1192 |
-
"epoch": 13.13,
|
| 1193 |
-
"learning_rate": 1.3871918698240918e-05,
|
| 1194 |
-
"loss": 0.0018,
|
| 1195 |
-
"step": 300825
|
| 1196 |
},
|
| 1197 |
{
|
| 1198 |
-
"epoch":
|
| 1199 |
-
"learning_rate": 1.
|
| 1200 |
-
"loss": 0.
|
| 1201 |
-
"step":
|
| 1202 |
-
},
|
| 1203 |
-
{
|
| 1204 |
-
"epoch": 13.28,
|
| 1205 |
-
"learning_rate": 1.276061364209383e-05,
|
| 1206 |
-
"loss": 0.0018,
|
| 1207 |
-
"step": 304263
|
| 1208 |
},
|
| 1209 |
{
|
| 1210 |
-
"epoch":
|
| 1211 |
-
"learning_rate": 1.
|
| 1212 |
-
"loss": 0.
|
| 1213 |
-
"step":
|
| 1214 |
},
|
| 1215 |
{
|
| 1216 |
-
"epoch":
|
| 1217 |
-
"learning_rate": 1.
|
| 1218 |
-
"loss": 0.
|
| 1219 |
-
"step":
|
| 1220 |
},
|
| 1221 |
{
|
| 1222 |
-
"epoch":
|
| 1223 |
-
"learning_rate": 1.
|
| 1224 |
-
"loss": 0.
|
| 1225 |
-
"step":
|
| 1226 |
},
|
| 1227 |
{
|
| 1228 |
-
"epoch":
|
| 1229 |
-
"learning_rate": 1.
|
| 1230 |
-
"loss": 0.
|
| 1231 |
-
"step":
|
| 1232 |
},
|
| 1233 |
{
|
| 1234 |
-
"epoch":
|
| 1235 |
-
"learning_rate":
|
| 1236 |
"loss": 0.0017,
|
| 1237 |
-
"step":
|
| 1238 |
},
|
| 1239 |
{
|
| 1240 |
-
"epoch":
|
| 1241 |
-
"learning_rate": 9.
|
| 1242 |
-
"loss": 0.
|
| 1243 |
-
"step":
|
| 1244 |
},
|
| 1245 |
{
|
| 1246 |
-
"epoch":
|
| 1247 |
-
"learning_rate":
|
| 1248 |
-
"loss": 0.
|
| 1249 |
-
"step":
|
| 1250 |
},
|
| 1251 |
{
|
| 1252 |
-
"epoch":
|
| 1253 |
-
"learning_rate": 8.
|
| 1254 |
-
"loss": 0.
|
| 1255 |
-
"step":
|
| 1256 |
},
|
| 1257 |
{
|
| 1258 |
-
"epoch":
|
| 1259 |
-
"learning_rate":
|
| 1260 |
-
"loss": 0.
|
| 1261 |
-
"step":
|
| 1262 |
},
|
| 1263 |
{
|
| 1264 |
-
"epoch":
|
| 1265 |
-
"
|
| 1266 |
-
"
|
| 1267 |
-
"
|
| 1268 |
-
"eval_runtime": 13.4713,
|
| 1269 |
-
"eval_samples_per_second": 18.632,
|
| 1270 |
-
"eval_steps_per_second": 1.262,
|
| 1271 |
-
"step": 320824
|
| 1272 |
},
|
| 1273 |
{
|
| 1274 |
-
"epoch":
|
| 1275 |
-
"learning_rate": 7.
|
| 1276 |
"loss": 0.0017,
|
| 1277 |
-
"step":
|
| 1278 |
},
|
| 1279 |
{
|
| 1280 |
-
"epoch":
|
| 1281 |
-
"learning_rate": 6.
|
| 1282 |
-
"loss": 0.
|
| 1283 |
-
"step":
|
| 1284 |
},
|
| 1285 |
{
|
| 1286 |
-
"epoch":
|
| 1287 |
-
"learning_rate": 6.
|
| 1288 |
-
"loss": 0.
|
| 1289 |
-
"step":
|
| 1290 |
},
|
| 1291 |
{
|
| 1292 |
-
"epoch":
|
| 1293 |
-
"learning_rate": 5.
|
| 1294 |
"loss": 0.0017,
|
| 1295 |
-
"step":
|
| 1296 |
},
|
| 1297 |
{
|
| 1298 |
-
"epoch":
|
| 1299 |
-
"learning_rate": 4.
|
| 1300 |
"loss": 0.0018,
|
| 1301 |
-
"step":
|
| 1302 |
},
|
| 1303 |
{
|
| 1304 |
-
"epoch":
|
| 1305 |
-
"learning_rate": 4.
|
| 1306 |
-
"loss": 0.
|
| 1307 |
-
"step":
|
| 1308 |
-
},
|
| 1309 |
-
{
|
| 1310 |
-
"epoch": 14.48,
|
| 1311 |
-
"learning_rate": 3.8701731929171274e-06,
|
| 1312 |
-
"loss": 0.0018,
|
| 1313 |
-
"step": 331767
|
| 1314 |
},
|
| 1315 |
{
|
| 1316 |
-
"epoch":
|
| 1317 |
-
"learning_rate": 3.
|
| 1318 |
-
"loss": 0.
|
| 1319 |
-
"step":
|
| 1320 |
},
|
| 1321 |
{
|
| 1322 |
-
"epoch":
|
| 1323 |
-
"learning_rate":
|
| 1324 |
-
"loss": 0.
|
| 1325 |
-
"step":
|
| 1326 |
},
|
| 1327 |
{
|
| 1328 |
-
"epoch":
|
| 1329 |
-
"learning_rate": 2.
|
| 1330 |
"loss": 0.0018,
|
| 1331 |
-
"step":
|
| 1332 |
},
|
| 1333 |
{
|
| 1334 |
-
"epoch":
|
| 1335 |
-
"learning_rate":
|
| 1336 |
"loss": 0.0017,
|
| 1337 |
-
"step":
|
| 1338 |
},
|
| 1339 |
{
|
| 1340 |
-
"epoch":
|
| 1341 |
-
"learning_rate": 1.
|
| 1342 |
"loss": 0.0018,
|
| 1343 |
-
"step":
|
| 1344 |
},
|
| 1345 |
{
|
| 1346 |
-
"epoch":
|
| 1347 |
-
"learning_rate":
|
| 1348 |
-
"loss": 0.
|
| 1349 |
-
"step":
|
| 1350 |
},
|
| 1351 |
{
|
| 1352 |
-
"epoch":
|
| 1353 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1354 |
"eval_max_distance": 8,
|
| 1355 |
"eval_mean_distance": 0,
|
| 1356 |
-
"eval_runtime":
|
| 1357 |
-
"eval_samples_per_second":
|
| 1358 |
-
"eval_steps_per_second":
|
| 1359 |
-
"step":
|
| 1360 |
-
},
|
| 1361 |
-
{
|
| 1362 |
-
"epoch":
|
| 1363 |
-
"step":
|
| 1364 |
-
"total_flos":
|
| 1365 |
-
"train_loss": 0.
|
| 1366 |
-
"train_runtime":
|
| 1367 |
-
"train_samples_per_second":
|
| 1368 |
-
"train_steps_per_second":
|
| 1369 |
}
|
| 1370 |
],
|
| 1371 |
-
"logging_steps":
|
| 1372 |
-
"max_steps":
|
| 1373 |
-
"num_train_epochs":
|
| 1374 |
-
"save_steps":
|
| 1375 |
-
"total_flos":
|
| 1376 |
"trial_name": null,
|
| 1377 |
"trial_params": null
|
| 1378 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 114970,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 8.697921196833957e-09,
|
| 14 |
+
"loss": 0.0,
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.03,
|
| 19 |
+
"learning_rate": 5.001304688179525e-06,
|
| 20 |
+
"loss": 0.0024,
|
| 21 |
+
"step": 575
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"epoch": 0.05,
|
| 25 |
+
"learning_rate": 1.000260937635905e-05,
|
| 26 |
+
"loss": 0.0025,
|
| 27 |
+
"step": 1150
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.08,
|
| 31 |
+
"learning_rate": 1.5003914064538576e-05,
|
| 32 |
+
"loss": 0.0021,
|
| 33 |
+
"step": 1725
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.1,
|
| 37 |
+
"learning_rate": 2.00052187527181e-05,
|
| 38 |
+
"loss": 0.002,
|
| 39 |
+
"step": 2300
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"epoch": 0.13,
|
| 43 |
+
"learning_rate": 2.500652344089763e-05,
|
| 44 |
+
"loss": 0.0024,
|
| 45 |
+
"step": 2875
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.15,
|
| 49 |
+
"learning_rate": 3.0007828129077153e-05,
|
| 50 |
+
"loss": 0.0021,
|
| 51 |
+
"step": 3450
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.18,
|
| 55 |
+
"learning_rate": 3.500913281725668e-05,
|
| 56 |
+
"loss": 0.0024,
|
| 57 |
+
"step": 4025
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 0.2,
|
| 61 |
+
"learning_rate": 4.00104375054362e-05,
|
| 62 |
+
"loss": 0.0021,
|
| 63 |
+
"step": 4600
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"epoch": 0.23,
|
| 67 |
+
"learning_rate": 4.501174219361573e-05,
|
| 68 |
+
"loss": 0.0021,
|
| 69 |
+
"step": 5175
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 0.25,
|
| 73 |
+
"learning_rate": 5.001304688179526e-05,
|
| 74 |
+
"loss": 0.0021,
|
| 75 |
+
"step": 5750
|
| 76 |
},
|
| 77 |
{
|
| 78 |
+
"epoch": 0.28,
|
| 79 |
+
"learning_rate": 5.501435156997478e-05,
|
| 80 |
+
"loss": 0.0022,
|
| 81 |
+
"step": 6325
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 0.3,
|
| 85 |
+
"learning_rate": 6.0015656258154306e-05,
|
| 86 |
+
"loss": 0.002,
|
| 87 |
+
"step": 6900
|
|
|
|
|
|
|
|
|
|
|
|
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 0.33,
|
| 91 |
+
"learning_rate": 6.501696094633383e-05,
|
| 92 |
+
"loss": 0.0021,
|
| 93 |
+
"step": 7475
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.35,
|
| 97 |
+
"learning_rate": 7.001826563451336e-05,
|
| 98 |
+
"loss": 0.0018,
|
| 99 |
+
"step": 8050
|
| 100 |
},
|
| 101 |
{
|
| 102 |
+
"epoch": 0.38,
|
| 103 |
+
"learning_rate": 7.501957032269288e-05,
|
| 104 |
+
"loss": 0.0021,
|
| 105 |
+
"step": 8625
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 0.4,
|
| 109 |
+
"learning_rate": 8.00208750108724e-05,
|
| 110 |
+
"loss": 0.0019,
|
| 111 |
+
"step": 9200
|
| 112 |
},
|
| 113 |
{
|
| 114 |
+
"epoch": 0.43,
|
| 115 |
+
"learning_rate": 8.502217969905193e-05,
|
| 116 |
+
"loss": 0.0023,
|
| 117 |
+
"step": 9775
|
| 118 |
},
|
| 119 |
{
|
| 120 |
+
"epoch": 0.45,
|
| 121 |
+
"learning_rate": 9.002348438723146e-05,
|
| 122 |
+
"loss": 0.0021,
|
| 123 |
+
"step": 10350
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 0.48,
|
| 127 |
+
"learning_rate": 9.502478907541099e-05,
|
| 128 |
+
"loss": 0.0021,
|
| 129 |
+
"step": 10925
|
| 130 |
},
|
| 131 |
{
|
| 132 |
+
"epoch": 0.5,
|
| 133 |
+
"learning_rate": 9.99971006929344e-05,
|
| 134 |
+
"loss": 0.0022,
|
| 135 |
+
"step": 11500
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 0.53,
|
| 139 |
+
"learning_rate": 9.944140017202556e-05,
|
| 140 |
+
"loss": 0.0025,
|
| 141 |
+
"step": 12075
|
| 142 |
},
|
| 143 |
{
|
| 144 |
+
"epoch": 0.55,
|
| 145 |
+
"learning_rate": 9.888569965111673e-05,
|
| 146 |
+
"loss": 0.0022,
|
| 147 |
+
"step": 12650
|
| 148 |
},
|
| 149 |
{
|
| 150 |
+
"epoch": 0.58,
|
| 151 |
+
"learning_rate": 9.832999913020789e-05,
|
| 152 |
+
"loss": 0.0022,
|
| 153 |
+
"step": 13225
|
| 154 |
},
|
| 155 |
{
|
| 156 |
+
"epoch": 0.6,
|
| 157 |
+
"learning_rate": 9.777429860929905e-05,
|
| 158 |
+
"loss": 0.002,
|
| 159 |
+
"step": 13800
|
| 160 |
},
|
| 161 |
{
|
| 162 |
+
"epoch": 0.63,
|
| 163 |
+
"learning_rate": 9.721859808839022e-05,
|
| 164 |
+
"loss": 0.0021,
|
| 165 |
+
"step": 14375
|
| 166 |
},
|
| 167 |
{
|
| 168 |
+
"epoch": 0.65,
|
| 169 |
+
"learning_rate": 9.666289756748138e-05,
|
| 170 |
+
"loss": 0.0023,
|
| 171 |
+
"step": 14950
|
|
|
|
|
|
|
|
|
|
|
|
|
| 172 |
},
|
| 173 |
{
|
| 174 |
+
"epoch": 0.68,
|
| 175 |
+
"learning_rate": 9.610719704657253e-05,
|
| 176 |
+
"loss": 0.0023,
|
| 177 |
+
"step": 15525
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 0.7,
|
| 181 |
+
"learning_rate": 9.55514965256637e-05,
|
| 182 |
+
"loss": 0.0023,
|
| 183 |
+
"step": 16100
|
| 184 |
},
|
| 185 |
{
|
| 186 |
+
"epoch": 0.73,
|
| 187 |
+
"learning_rate": 9.499579600475486e-05,
|
| 188 |
+
"loss": 0.002,
|
| 189 |
+
"step": 16675
|
| 190 |
},
|
| 191 |
{
|
| 192 |
+
"epoch": 0.75,
|
| 193 |
+
"learning_rate": 9.444009548384603e-05,
|
| 194 |
+
"loss": 0.0025,
|
| 195 |
+
"step": 17250
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 0.78,
|
| 199 |
+
"learning_rate": 9.388439496293719e-05,
|
| 200 |
+
"loss": 0.0023,
|
| 201 |
+
"step": 17825
|
| 202 |
},
|
| 203 |
{
|
| 204 |
+
"epoch": 0.8,
|
| 205 |
+
"learning_rate": 9.332869444202836e-05,
|
| 206 |
+
"loss": 0.0026,
|
| 207 |
+
"step": 18400
|
| 208 |
},
|
| 209 |
{
|
| 210 |
+
"epoch": 0.83,
|
| 211 |
+
"learning_rate": 9.277299392111952e-05,
|
| 212 |
+
"loss": 0.0025,
|
| 213 |
+
"step": 18975
|
| 214 |
},
|
| 215 |
{
|
| 216 |
+
"epoch": 0.85,
|
| 217 |
+
"learning_rate": 9.221729340021069e-05,
|
| 218 |
+
"loss": 0.0027,
|
| 219 |
+
"step": 19550
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 0.88,
|
| 223 |
+
"learning_rate": 9.166159287930185e-05,
|
| 224 |
+
"loss": 0.0024,
|
| 225 |
+
"step": 20125
|
| 226 |
},
|
| 227 |
{
|
| 228 |
+
"epoch": 0.9,
|
| 229 |
+
"learning_rate": 9.110589235839302e-05,
|
| 230 |
+
"loss": 0.0022,
|
| 231 |
+
"step": 20700
|
| 232 |
},
|
| 233 |
{
|
| 234 |
+
"epoch": 0.93,
|
| 235 |
+
"learning_rate": 9.055019183748418e-05,
|
| 236 |
+
"loss": 0.0026,
|
| 237 |
+
"step": 21275
|
| 238 |
},
|
| 239 |
{
|
| 240 |
+
"epoch": 0.95,
|
| 241 |
+
"learning_rate": 8.999449131657535e-05,
|
| 242 |
+
"loss": 0.0025,
|
| 243 |
+
"step": 21850
|
| 244 |
},
|
| 245 |
{
|
| 246 |
+
"epoch": 0.98,
|
| 247 |
+
"learning_rate": 8.94387907956665e-05,
|
| 248 |
+
"loss": 0.0024,
|
| 249 |
+
"step": 22425
|
| 250 |
},
|
| 251 |
{
|
| 252 |
+
"epoch": 1.0,
|
| 253 |
+
"eval_loss": 0.02637363225221634,
|
| 254 |
"eval_max_distance": 8,
|
| 255 |
"eval_mean_distance": 0,
|
| 256 |
+
"eval_runtime": 23.0018,
|
| 257 |
+
"eval_samples_per_second": 11.217,
|
| 258 |
+
"eval_steps_per_second": 0.783,
|
| 259 |
+
"step": 22994
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 260 |
},
|
| 261 |
{
|
| 262 |
+
"epoch": 1.0,
|
| 263 |
+
"learning_rate": 8.888309027475768e-05,
|
| 264 |
+
"loss": 0.0026,
|
| 265 |
+
"step": 23000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 266 |
},
|
| 267 |
{
|
| 268 |
+
"epoch": 1.03,
|
| 269 |
+
"learning_rate": 8.832738975384883e-05,
|
| 270 |
+
"loss": 0.0019,
|
| 271 |
+
"step": 23575
|
| 272 |
},
|
| 273 |
{
|
| 274 |
+
"epoch": 1.05,
|
| 275 |
+
"learning_rate": 8.777168923294e-05,
|
| 276 |
+
"loss": 0.002,
|
| 277 |
+
"step": 24150
|
| 278 |
},
|
| 279 |
{
|
| 280 |
+
"epoch": 1.08,
|
| 281 |
+
"learning_rate": 8.721598871203116e-05,
|
| 282 |
+
"loss": 0.002,
|
| 283 |
+
"step": 24725
|
| 284 |
},
|
| 285 |
{
|
| 286 |
+
"epoch": 1.1,
|
| 287 |
+
"learning_rate": 8.666028819112233e-05,
|
| 288 |
+
"loss": 0.0021,
|
| 289 |
+
"step": 25300
|
| 290 |
},
|
| 291 |
{
|
| 292 |
+
"epoch": 1.13,
|
| 293 |
+
"learning_rate": 8.610458767021349e-05,
|
| 294 |
+
"loss": 0.0022,
|
| 295 |
+
"step": 25875
|
| 296 |
},
|
| 297 |
{
|
| 298 |
+
"epoch": 1.15,
|
| 299 |
+
"learning_rate": 8.554888714930466e-05,
|
| 300 |
+
"loss": 0.0022,
|
| 301 |
+
"step": 26450
|
| 302 |
},
|
| 303 |
{
|
| 304 |
+
"epoch": 1.18,
|
| 305 |
+
"learning_rate": 8.499318662839582e-05,
|
| 306 |
+
"loss": 0.0023,
|
| 307 |
+
"step": 27025
|
| 308 |
},
|
| 309 |
{
|
| 310 |
+
"epoch": 1.2,
|
| 311 |
+
"learning_rate": 8.443748610748699e-05,
|
| 312 |
+
"loss": 0.0023,
|
| 313 |
+
"step": 27600
|
| 314 |
},
|
| 315 |
{
|
| 316 |
+
"epoch": 1.23,
|
| 317 |
+
"learning_rate": 8.388178558657815e-05,
|
| 318 |
+
"loss": 0.002,
|
| 319 |
+
"step": 28175
|
| 320 |
},
|
| 321 |
{
|
| 322 |
+
"epoch": 1.25,
|
| 323 |
+
"learning_rate": 8.33260850656693e-05,
|
| 324 |
+
"loss": 0.0022,
|
| 325 |
+
"step": 28750
|
| 326 |
},
|
| 327 |
{
|
| 328 |
+
"epoch": 1.28,
|
| 329 |
+
"learning_rate": 8.277038454476048e-05,
|
| 330 |
+
"loss": 0.0022,
|
| 331 |
+
"step": 29325
|
| 332 |
},
|
| 333 |
{
|
| 334 |
+
"epoch": 1.3,
|
| 335 |
+
"learning_rate": 8.221468402385163e-05,
|
| 336 |
+
"loss": 0.002,
|
| 337 |
+
"step": 29900
|
|
|
|
|
|
|
|
|
|
|
|
|
| 338 |
},
|
| 339 |
{
|
| 340 |
+
"epoch": 1.33,
|
| 341 |
+
"learning_rate": 8.165898350294279e-05,
|
| 342 |
+
"loss": 0.0023,
|
| 343 |
+
"step": 30475
|
| 344 |
},
|
| 345 |
{
|
| 346 |
+
"epoch": 1.35,
|
| 347 |
+
"learning_rate": 8.110328298203396e-05,
|
| 348 |
+
"loss": 0.0026,
|
| 349 |
+
"step": 31050
|
| 350 |
},
|
| 351 |
{
|
| 352 |
+
"epoch": 1.38,
|
| 353 |
+
"learning_rate": 8.054758246112512e-05,
|
| 354 |
+
"loss": 0.0022,
|
| 355 |
+
"step": 31625
|
| 356 |
},
|
| 357 |
{
|
| 358 |
+
"epoch": 1.4,
|
| 359 |
+
"learning_rate": 7.999188194021629e-05,
|
| 360 |
+
"loss": 0.0023,
|
| 361 |
+
"step": 32200
|
| 362 |
},
|
| 363 |
{
|
| 364 |
+
"epoch": 1.43,
|
| 365 |
+
"learning_rate": 7.943618141930745e-05,
|
| 366 |
+
"loss": 0.0023,
|
| 367 |
+
"step": 32775
|
| 368 |
},
|
| 369 |
{
|
| 370 |
+
"epoch": 1.45,
|
| 371 |
+
"learning_rate": 7.888048089839862e-05,
|
| 372 |
+
"loss": 0.0024,
|
| 373 |
+
"step": 33350
|
| 374 |
},
|
| 375 |
{
|
| 376 |
+
"epoch": 1.48,
|
| 377 |
+
"learning_rate": 7.832478037748978e-05,
|
| 378 |
+
"loss": 0.0024,
|
| 379 |
+
"step": 33925
|
| 380 |
},
|
| 381 |
{
|
| 382 |
+
"epoch": 1.5,
|
| 383 |
+
"learning_rate": 7.776907985658095e-05,
|
| 384 |
+
"loss": 0.0025,
|
| 385 |
+
"step": 34500
|
| 386 |
},
|
| 387 |
{
|
| 388 |
+
"epoch": 1.53,
|
| 389 |
+
"learning_rate": 7.721337933567211e-05,
|
| 390 |
+
"loss": 0.0023,
|
| 391 |
+
"step": 35075
|
| 392 |
},
|
| 393 |
{
|
| 394 |
+
"epoch": 1.55,
|
| 395 |
+
"learning_rate": 7.665767881476328e-05,
|
| 396 |
+
"loss": 0.0021,
|
| 397 |
+
"step": 35650
|
| 398 |
},
|
| 399 |
{
|
| 400 |
+
"epoch": 1.58,
|
| 401 |
+
"learning_rate": 7.610197829385444e-05,
|
| 402 |
+
"loss": 0.0022,
|
| 403 |
+
"step": 36225
|
| 404 |
},
|
| 405 |
{
|
| 406 |
+
"epoch": 1.6,
|
| 407 |
+
"learning_rate": 7.554627777294561e-05,
|
| 408 |
+
"loss": 0.002,
|
| 409 |
+
"step": 36800
|
| 410 |
},
|
| 411 |
{
|
| 412 |
+
"epoch": 1.63,
|
| 413 |
+
"learning_rate": 7.499057725203676e-05,
|
| 414 |
+
"loss": 0.0021,
|
| 415 |
+
"step": 37375
|
| 416 |
},
|
| 417 |
{
|
| 418 |
+
"epoch": 1.65,
|
| 419 |
+
"learning_rate": 7.443487673112794e-05,
|
| 420 |
+
"loss": 0.0024,
|
| 421 |
+
"step": 37950
|
|
|
|
|
|
|
|
|
|
|
|
|
| 422 |
},
|
| 423 |
{
|
| 424 |
+
"epoch": 1.68,
|
| 425 |
+
"learning_rate": 7.38791762102191e-05,
|
| 426 |
+
"loss": 0.0024,
|
| 427 |
+
"step": 38525
|
| 428 |
},
|
| 429 |
{
|
| 430 |
+
"epoch": 1.7,
|
| 431 |
+
"learning_rate": 7.332347568931026e-05,
|
| 432 |
+
"loss": 0.0022,
|
| 433 |
+
"step": 39100
|
| 434 |
},
|
| 435 |
{
|
| 436 |
+
"epoch": 1.73,
|
| 437 |
+
"learning_rate": 7.276777516840142e-05,
|
| 438 |
+
"loss": 0.0024,
|
| 439 |
+
"step": 39675
|
| 440 |
},
|
| 441 |
{
|
| 442 |
+
"epoch": 1.75,
|
| 443 |
+
"learning_rate": 7.221207464749259e-05,
|
| 444 |
+
"loss": 0.0023,
|
| 445 |
+
"step": 40250
|
| 446 |
},
|
| 447 |
{
|
| 448 |
+
"epoch": 1.78,
|
| 449 |
+
"learning_rate": 7.165637412658375e-05,
|
| 450 |
+
"loss": 0.0023,
|
| 451 |
+
"step": 40825
|
| 452 |
},
|
| 453 |
{
|
| 454 |
+
"epoch": 1.8,
|
| 455 |
+
"learning_rate": 7.110067360567492e-05,
|
| 456 |
+
"loss": 0.0022,
|
| 457 |
+
"step": 41400
|
| 458 |
},
|
| 459 |
{
|
| 460 |
+
"epoch": 1.83,
|
| 461 |
+
"learning_rate": 7.054497308476608e-05,
|
| 462 |
+
"loss": 0.0023,
|
| 463 |
+
"step": 41975
|
| 464 |
},
|
| 465 |
{
|
| 466 |
+
"epoch": 1.85,
|
| 467 |
+
"learning_rate": 6.998927256385725e-05,
|
| 468 |
+
"loss": 0.0023,
|
| 469 |
+
"step": 42550
|
| 470 |
},
|
| 471 |
{
|
| 472 |
+
"epoch": 1.88,
|
| 473 |
+
"learning_rate": 6.943357204294841e-05,
|
| 474 |
+
"loss": 0.0023,
|
| 475 |
+
"step": 43125
|
| 476 |
},
|
| 477 |
{
|
| 478 |
+
"epoch": 1.9,
|
| 479 |
+
"learning_rate": 6.887787152203957e-05,
|
| 480 |
+
"loss": 0.0024,
|
| 481 |
+
"step": 43700
|
| 482 |
},
|
| 483 |
{
|
| 484 |
+
"epoch": 1.93,
|
| 485 |
+
"learning_rate": 6.832217100113074e-05,
|
| 486 |
+
"loss": 0.0024,
|
| 487 |
+
"step": 44275
|
| 488 |
},
|
| 489 |
{
|
| 490 |
+
"epoch": 1.95,
|
| 491 |
+
"learning_rate": 6.77664704802219e-05,
|
| 492 |
+
"loss": 0.0022,
|
| 493 |
+
"step": 44850
|
| 494 |
},
|
| 495 |
{
|
| 496 |
+
"epoch": 1.98,
|
| 497 |
+
"learning_rate": 6.721076995931305e-05,
|
| 498 |
+
"loss": 0.0022,
|
| 499 |
+
"step": 45425
|
| 500 |
},
|
| 501 |
{
|
| 502 |
+
"epoch": 2.0,
|
| 503 |
+
"eval_loss": 0.025934860110282898,
|
| 504 |
"eval_max_distance": 8,
|
| 505 |
"eval_mean_distance": 0,
|
| 506 |
+
"eval_runtime": 21.6745,
|
| 507 |
+
"eval_samples_per_second": 11.903,
|
| 508 |
+
"eval_steps_per_second": 0.83,
|
| 509 |
+
"step": 45988
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 510 |
},
|
| 511 |
{
|
| 512 |
+
"epoch": 2.0,
|
| 513 |
+
"learning_rate": 6.665506943840422e-05,
|
| 514 |
+
"loss": 0.0024,
|
| 515 |
+
"step": 46000
|
| 516 |
},
|
| 517 |
{
|
| 518 |
+
"epoch": 2.03,
|
| 519 |
+
"learning_rate": 6.609936891749538e-05,
|
| 520 |
+
"loss": 0.0019,
|
| 521 |
+
"step": 46575
|
| 522 |
},
|
| 523 |
{
|
| 524 |
+
"epoch": 2.05,
|
| 525 |
+
"learning_rate": 6.554366839658655e-05,
|
| 526 |
+
"loss": 0.0021,
|
| 527 |
+
"step": 47150
|
| 528 |
},
|
| 529 |
{
|
| 530 |
+
"epoch": 2.08,
|
| 531 |
+
"learning_rate": 6.498796787567771e-05,
|
| 532 |
+
"loss": 0.0019,
|
| 533 |
+
"step": 47725
|
| 534 |
},
|
| 535 |
{
|
| 536 |
+
"epoch": 2.1,
|
| 537 |
+
"learning_rate": 6.443226735476888e-05,
|
| 538 |
+
"loss": 0.0021,
|
| 539 |
+
"step": 48300
|
| 540 |
},
|
| 541 |
{
|
| 542 |
+
"epoch": 2.13,
|
| 543 |
+
"learning_rate": 6.387656683386004e-05,
|
| 544 |
+
"loss": 0.0018,
|
| 545 |
+
"step": 48875
|
| 546 |
},
|
| 547 |
{
|
| 548 |
+
"epoch": 2.15,
|
| 549 |
+
"learning_rate": 6.332086631295121e-05,
|
| 550 |
+
"loss": 0.002,
|
| 551 |
+
"step": 49450
|
| 552 |
},
|
| 553 |
{
|
| 554 |
+
"epoch": 2.18,
|
| 555 |
+
"learning_rate": 6.276516579204237e-05,
|
| 556 |
+
"loss": 0.0021,
|
| 557 |
+
"step": 50025
|
| 558 |
},
|
| 559 |
{
|
| 560 |
+
"epoch": 2.2,
|
| 561 |
+
"learning_rate": 6.220946527113354e-05,
|
| 562 |
+
"loss": 0.002,
|
| 563 |
+
"step": 50600
|
| 564 |
},
|
| 565 |
{
|
| 566 |
+
"epoch": 2.23,
|
| 567 |
+
"learning_rate": 6.16537647502247e-05,
|
| 568 |
+
"loss": 0.0019,
|
| 569 |
+
"step": 51175
|
| 570 |
},
|
| 571 |
{
|
| 572 |
+
"epoch": 2.25,
|
| 573 |
+
"learning_rate": 6.109806422931587e-05,
|
| 574 |
+
"loss": 0.002,
|
| 575 |
+
"step": 51750
|
| 576 |
},
|
| 577 |
{
|
| 578 |
+
"epoch": 2.28,
|
| 579 |
+
"learning_rate": 6.0542363708407024e-05,
|
| 580 |
+
"loss": 0.0021,
|
| 581 |
+
"step": 52325
|
| 582 |
},
|
| 583 |
{
|
| 584 |
+
"epoch": 2.3,
|
| 585 |
+
"learning_rate": 5.9986663187498195e-05,
|
| 586 |
+
"loss": 0.0021,
|
| 587 |
+
"step": 52900
|
|
|
|
|
|
|
|
|
|
|
|
|
| 588 |
},
|
| 589 |
{
|
| 590 |
+
"epoch": 2.33,
|
| 591 |
+
"learning_rate": 5.943096266658935e-05,
|
| 592 |
+
"loss": 0.0019,
|
| 593 |
+
"step": 53475
|
| 594 |
},
|
| 595 |
{
|
| 596 |
+
"epoch": 2.35,
|
| 597 |
+
"learning_rate": 5.8875262145680524e-05,
|
| 598 |
+
"loss": 0.0018,
|
| 599 |
+
"step": 54050
|
| 600 |
},
|
| 601 |
{
|
| 602 |
+
"epoch": 2.38,
|
| 603 |
+
"learning_rate": 5.831956162477168e-05,
|
| 604 |
+
"loss": 0.0021,
|
| 605 |
+
"step": 54625
|
| 606 |
},
|
| 607 |
{
|
| 608 |
+
"epoch": 2.4,
|
| 609 |
+
"learning_rate": 5.7763861103862846e-05,
|
| 610 |
+
"loss": 0.0021,
|
| 611 |
+
"step": 55200
|
| 612 |
},
|
| 613 |
{
|
| 614 |
+
"epoch": 2.43,
|
| 615 |
+
"learning_rate": 5.720816058295401e-05,
|
| 616 |
+
"loss": 0.0019,
|
| 617 |
+
"step": 55775
|
| 618 |
},
|
| 619 |
{
|
| 620 |
+
"epoch": 2.45,
|
| 621 |
+
"learning_rate": 5.6652460062045174e-05,
|
| 622 |
+
"loss": 0.002,
|
| 623 |
+
"step": 56350
|
| 624 |
},
|
| 625 |
{
|
| 626 |
+
"epoch": 2.48,
|
| 627 |
+
"learning_rate": 5.609675954113633e-05,
|
| 628 |
+
"loss": 0.0022,
|
| 629 |
+
"step": 56925
|
| 630 |
},
|
| 631 |
{
|
| 632 |
+
"epoch": 2.5,
|
| 633 |
+
"learning_rate": 5.55410590202275e-05,
|
| 634 |
+
"loss": 0.0018,
|
| 635 |
+
"step": 57500
|
| 636 |
},
|
| 637 |
{
|
| 638 |
+
"epoch": 2.53,
|
| 639 |
+
"learning_rate": 5.498535849931866e-05,
|
| 640 |
+
"loss": 0.0023,
|
| 641 |
+
"step": 58075
|
| 642 |
},
|
| 643 |
{
|
| 644 |
+
"epoch": 2.55,
|
| 645 |
+
"learning_rate": 5.442965797840983e-05,
|
| 646 |
+
"loss": 0.0021,
|
| 647 |
+
"step": 58650
|
| 648 |
},
|
| 649 |
{
|
| 650 |
+
"epoch": 2.58,
|
| 651 |
+
"learning_rate": 5.387395745750099e-05,
|
| 652 |
+
"loss": 0.002,
|
| 653 |
+
"step": 59225
|
| 654 |
},
|
| 655 |
{
|
| 656 |
+
"epoch": 2.6,
|
| 657 |
+
"learning_rate": 5.331825693659216e-05,
|
| 658 |
+
"loss": 0.0019,
|
| 659 |
+
"step": 59800
|
| 660 |
},
|
| 661 |
{
|
| 662 |
+
"epoch": 2.63,
|
| 663 |
+
"learning_rate": 5.276255641568332e-05,
|
| 664 |
+
"loss": 0.0021,
|
| 665 |
+
"step": 60375
|
| 666 |
},
|
| 667 |
{
|
| 668 |
+
"epoch": 2.65,
|
| 669 |
+
"learning_rate": 5.220685589477449e-05,
|
| 670 |
+
"loss": 0.0022,
|
| 671 |
+
"step": 60950
|
|
|
|
|
|
|
|
|
|
|
|
|
| 672 |
},
|
| 673 |
{
|
| 674 |
+
"epoch": 2.68,
|
| 675 |
+
"learning_rate": 5.1651155373865647e-05,
|
| 676 |
+
"loss": 0.0017,
|
| 677 |
+
"step": 61525
|
| 678 |
},
|
| 679 |
{
|
| 680 |
+
"epoch": 2.7,
|
| 681 |
+
"learning_rate": 5.109545485295682e-05,
|
| 682 |
+
"loss": 0.0019,
|
| 683 |
+
"step": 62100
|
| 684 |
},
|
| 685 |
{
|
| 686 |
+
"epoch": 2.73,
|
| 687 |
+
"learning_rate": 5.0539754332047975e-05,
|
| 688 |
+
"loss": 0.002,
|
| 689 |
+
"step": 62675
|
| 690 |
},
|
| 691 |
{
|
| 692 |
+
"epoch": 2.75,
|
| 693 |
+
"learning_rate": 4.998405381113914e-05,
|
| 694 |
+
"loss": 0.0019,
|
| 695 |
+
"step": 63250
|
| 696 |
},
|
| 697 |
{
|
| 698 |
+
"epoch": 2.78,
|
| 699 |
+
"learning_rate": 4.9428353290230304e-05,
|
| 700 |
+
"loss": 0.0022,
|
| 701 |
+
"step": 63825
|
| 702 |
},
|
| 703 |
{
|
| 704 |
+
"epoch": 2.8,
|
| 705 |
+
"learning_rate": 4.887265276932147e-05,
|
| 706 |
+
"loss": 0.0021,
|
| 707 |
+
"step": 64400
|
| 708 |
},
|
| 709 |
{
|
| 710 |
+
"epoch": 2.83,
|
| 711 |
+
"learning_rate": 4.831695224841263e-05,
|
| 712 |
+
"loss": 0.0023,
|
| 713 |
+
"step": 64975
|
| 714 |
},
|
| 715 |
{
|
| 716 |
+
"epoch": 2.85,
|
| 717 |
+
"learning_rate": 4.77612517275038e-05,
|
| 718 |
+
"loss": 0.002,
|
| 719 |
+
"step": 65550
|
| 720 |
},
|
| 721 |
{
|
| 722 |
+
"epoch": 2.88,
|
| 723 |
+
"learning_rate": 4.720555120659496e-05,
|
| 724 |
+
"loss": 0.002,
|
| 725 |
+
"step": 66125
|
| 726 |
},
|
| 727 |
{
|
| 728 |
+
"epoch": 2.9,
|
| 729 |
+
"learning_rate": 4.6649850685686126e-05,
|
| 730 |
+
"loss": 0.0021,
|
| 731 |
+
"step": 66700
|
| 732 |
},
|
| 733 |
{
|
| 734 |
+
"epoch": 2.93,
|
| 735 |
+
"learning_rate": 4.609415016477729e-05,
|
| 736 |
+
"loss": 0.0021,
|
| 737 |
+
"step": 67275
|
| 738 |
},
|
| 739 |
{
|
| 740 |
+
"epoch": 2.95,
|
| 741 |
+
"learning_rate": 4.5538449643868454e-05,
|
| 742 |
+
"loss": 0.002,
|
| 743 |
+
"step": 67850
|
| 744 |
},
|
| 745 |
{
|
| 746 |
+
"epoch": 2.98,
|
| 747 |
+
"learning_rate": 4.498274912295962e-05,
|
| 748 |
+
"loss": 0.0019,
|
| 749 |
+
"step": 68425
|
| 750 |
},
|
| 751 |
{
|
| 752 |
+
"epoch": 3.0,
|
| 753 |
+
"eval_loss": 0.029171258211135864,
|
| 754 |
"eval_max_distance": 8,
|
| 755 |
"eval_mean_distance": 0,
|
| 756 |
+
"eval_runtime": 20.5415,
|
| 757 |
+
"eval_samples_per_second": 12.56,
|
| 758 |
+
"eval_steps_per_second": 0.876,
|
| 759 |
+
"step": 68982
|
| 760 |
},
|
| 761 |
{
|
| 762 |
+
"epoch": 3.0,
|
| 763 |
+
"learning_rate": 4.442704860205078e-05,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 764 |
"loss": 0.0021,
|
| 765 |
+
"step": 69000
|
| 766 |
},
|
| 767 |
{
|
| 768 |
+
"epoch": 3.03,
|
| 769 |
+
"learning_rate": 4.387134808114195e-05,
|
| 770 |
+
"loss": 0.0017,
|
| 771 |
+
"step": 69575
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 772 |
},
|
| 773 |
{
|
| 774 |
+
"epoch": 3.05,
|
| 775 |
+
"learning_rate": 4.3315647560233105e-05,
|
| 776 |
+
"loss": 0.002,
|
| 777 |
+
"step": 70150
|
| 778 |
},
|
| 779 |
{
|
| 780 |
+
"epoch": 3.08,
|
| 781 |
+
"learning_rate": 4.275994703932427e-05,
|
| 782 |
+
"loss": 0.0016,
|
| 783 |
+
"step": 70725
|
| 784 |
},
|
| 785 |
{
|
| 786 |
+
"epoch": 3.1,
|
| 787 |
+
"learning_rate": 4.2204246518415434e-05,
|
| 788 |
+
"loss": 0.0018,
|
| 789 |
+
"step": 71300
|
| 790 |
},
|
| 791 |
{
|
| 792 |
+
"epoch": 3.13,
|
| 793 |
+
"learning_rate": 4.16485459975066e-05,
|
| 794 |
+
"loss": 0.0018,
|
| 795 |
+
"step": 71875
|
| 796 |
},
|
| 797 |
{
|
| 798 |
+
"epoch": 3.15,
|
| 799 |
+
"learning_rate": 4.109284547659776e-05,
|
| 800 |
+
"loss": 0.0018,
|
| 801 |
+
"step": 72450
|
| 802 |
},
|
| 803 |
{
|
| 804 |
+
"epoch": 3.18,
|
| 805 |
+
"learning_rate": 4.0537144955688927e-05,
|
| 806 |
+
"loss": 0.0018,
|
| 807 |
+
"step": 73025
|
| 808 |
},
|
| 809 |
{
|
| 810 |
+
"epoch": 3.2,
|
| 811 |
+
"learning_rate": 3.998144443478009e-05,
|
| 812 |
+
"loss": 0.002,
|
| 813 |
+
"step": 73600
|
| 814 |
},
|
| 815 |
{
|
| 816 |
+
"epoch": 3.23,
|
| 817 |
+
"learning_rate": 3.9425743913871255e-05,
|
| 818 |
+
"loss": 0.002,
|
| 819 |
+
"step": 74175
|
| 820 |
},
|
| 821 |
{
|
| 822 |
+
"epoch": 3.25,
|
| 823 |
+
"learning_rate": 3.887004339296242e-05,
|
| 824 |
+
"loss": 0.0019,
|
| 825 |
+
"step": 74750
|
| 826 |
},
|
| 827 |
{
|
| 828 |
+
"epoch": 3.28,
|
| 829 |
+
"learning_rate": 3.8314342872053584e-05,
|
| 830 |
+
"loss": 0.0018,
|
| 831 |
+
"step": 75325
|
|
|
|
|
|
|
|
|
|
|
|
|
| 832 |
},
|
| 833 |
{
|
| 834 |
+
"epoch": 3.3,
|
| 835 |
+
"learning_rate": 3.775864235114475e-05,
|
| 836 |
+
"loss": 0.0018,
|
| 837 |
+
"step": 75900
|
| 838 |
},
|
| 839 |
{
|
| 840 |
+
"epoch": 3.33,
|
| 841 |
+
"learning_rate": 3.720294183023591e-05,
|
| 842 |
+
"loss": 0.0017,
|
| 843 |
+
"step": 76475
|
| 844 |
},
|
| 845 |
{
|
| 846 |
+
"epoch": 3.35,
|
| 847 |
+
"learning_rate": 3.664724130932708e-05,
|
| 848 |
+
"loss": 0.0017,
|
| 849 |
+
"step": 77050
|
| 850 |
},
|
| 851 |
{
|
| 852 |
+
"epoch": 3.38,
|
| 853 |
+
"learning_rate": 3.6091540788418234e-05,
|
| 854 |
+
"loss": 0.0018,
|
| 855 |
+
"step": 77625
|
| 856 |
},
|
| 857 |
{
|
| 858 |
+
"epoch": 3.4,
|
| 859 |
+
"learning_rate": 3.55358402675094e-05,
|
| 860 |
+
"loss": 0.0018,
|
| 861 |
+
"step": 78200
|
| 862 |
},
|
| 863 |
{
|
| 864 |
+
"epoch": 3.43,
|
| 865 |
+
"learning_rate": 3.498013974660056e-05,
|
| 866 |
+
"loss": 0.0016,
|
| 867 |
+
"step": 78775
|
| 868 |
},
|
| 869 |
{
|
| 870 |
+
"epoch": 3.45,
|
| 871 |
+
"learning_rate": 3.442443922569173e-05,
|
| 872 |
+
"loss": 0.0016,
|
| 873 |
+
"step": 79350
|
| 874 |
},
|
| 875 |
{
|
| 876 |
+
"epoch": 3.48,
|
| 877 |
+
"learning_rate": 3.386873870478289e-05,
|
| 878 |
+
"loss": 0.0018,
|
| 879 |
+
"step": 79925
|
| 880 |
},
|
| 881 |
{
|
| 882 |
+
"epoch": 3.5,
|
| 883 |
+
"learning_rate": 3.3313038183874056e-05,
|
| 884 |
+
"loss": 0.0017,
|
| 885 |
+
"step": 80500
|
| 886 |
},
|
| 887 |
{
|
| 888 |
+
"epoch": 3.53,
|
| 889 |
+
"learning_rate": 3.275733766296522e-05,
|
| 890 |
+
"loss": 0.0017,
|
| 891 |
+
"step": 81075
|
| 892 |
},
|
| 893 |
{
|
| 894 |
+
"epoch": 3.55,
|
| 895 |
+
"learning_rate": 3.2201637142056385e-05,
|
| 896 |
+
"loss": 0.0016,
|
| 897 |
+
"step": 81650
|
| 898 |
},
|
| 899 |
{
|
| 900 |
+
"epoch": 3.58,
|
| 901 |
+
"learning_rate": 3.164593662114755e-05,
|
| 902 |
"loss": 0.002,
|
| 903 |
+
"step": 82225
|
| 904 |
},
|
| 905 |
{
|
| 906 |
+
"epoch": 3.6,
|
| 907 |
+
"learning_rate": 3.1090236100238714e-05,
|
| 908 |
+
"loss": 0.0018,
|
| 909 |
+
"step": 82800
|
| 910 |
},
|
| 911 |
{
|
| 912 |
+
"epoch": 3.63,
|
| 913 |
+
"learning_rate": 3.053453557932988e-05,
|
| 914 |
+
"loss": 0.0016,
|
| 915 |
+
"step": 83375
|
|
|
|
|
|
|
|
|
|
|
|
|
| 916 |
},
|
| 917 |
{
|
| 918 |
+
"epoch": 3.65,
|
| 919 |
+
"learning_rate": 2.997883505842104e-05,
|
| 920 |
+
"loss": 0.0017,
|
| 921 |
+
"step": 83950
|
| 922 |
},
|
| 923 |
{
|
| 924 |
+
"epoch": 3.68,
|
| 925 |
+
"learning_rate": 2.9423134537512203e-05,
|
| 926 |
+
"loss": 0.0019,
|
| 927 |
+
"step": 84525
|
| 928 |
},
|
| 929 |
{
|
| 930 |
+
"epoch": 3.7,
|
| 931 |
+
"learning_rate": 2.8867434016603368e-05,
|
| 932 |
+
"loss": 0.0018,
|
| 933 |
+
"step": 85100
|
| 934 |
},
|
| 935 |
{
|
| 936 |
+
"epoch": 3.73,
|
| 937 |
+
"learning_rate": 2.8311733495694532e-05,
|
| 938 |
+
"loss": 0.0017,
|
| 939 |
+
"step": 85675
|
| 940 |
},
|
| 941 |
{
|
| 942 |
+
"epoch": 3.75,
|
| 943 |
+
"learning_rate": 2.7756032974785696e-05,
|
| 944 |
+
"loss": 0.0017,
|
| 945 |
+
"step": 86250
|
| 946 |
},
|
| 947 |
{
|
| 948 |
+
"epoch": 3.78,
|
| 949 |
+
"learning_rate": 2.720033245387686e-05,
|
| 950 |
"loss": 0.0019,
|
| 951 |
+
"step": 86825
|
| 952 |
},
|
| 953 |
{
|
| 954 |
+
"epoch": 3.8,
|
| 955 |
+
"learning_rate": 2.664463193296802e-05,
|
| 956 |
"loss": 0.002,
|
| 957 |
+
"step": 87400
|
| 958 |
},
|
| 959 |
{
|
| 960 |
+
"epoch": 3.83,
|
| 961 |
+
"learning_rate": 2.6088931412059186e-05,
|
| 962 |
+
"loss": 0.0019,
|
| 963 |
+
"step": 87975
|
| 964 |
},
|
| 965 |
{
|
| 966 |
+
"epoch": 3.85,
|
| 967 |
+
"learning_rate": 2.553323089115035e-05,
|
| 968 |
+
"loss": 0.0017,
|
| 969 |
+
"step": 88550
|
| 970 |
},
|
| 971 |
{
|
| 972 |
+
"epoch": 3.88,
|
| 973 |
+
"learning_rate": 2.4977530370241514e-05,
|
| 974 |
+
"loss": 0.0018,
|
| 975 |
+
"step": 89125
|
| 976 |
},
|
| 977 |
{
|
| 978 |
+
"epoch": 3.9,
|
| 979 |
+
"learning_rate": 2.442182984933268e-05,
|
| 980 |
+
"loss": 0.0018,
|
| 981 |
+
"step": 89700
|
| 982 |
},
|
| 983 |
{
|
| 984 |
+
"epoch": 3.93,
|
| 985 |
+
"learning_rate": 2.3866129328423843e-05,
|
| 986 |
+
"loss": 0.0018,
|
| 987 |
+
"step": 90275
|
| 988 |
},
|
| 989 |
{
|
| 990 |
+
"epoch": 3.95,
|
| 991 |
+
"learning_rate": 2.3310428807515004e-05,
|
| 992 |
"loss": 0.0019,
|
| 993 |
+
"step": 90850
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 3.98,
|
| 997 |
+
"learning_rate": 2.275472828660617e-05,
|
| 998 |
+
"loss": 0.0016,
|
| 999 |
+
"step": 91425
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
+
"epoch": 4.0,
|
| 1003 |
+
"eval_loss": 0.02807791158556938,
|
| 1004 |
"eval_max_distance": 8,
|
| 1005 |
"eval_mean_distance": 0,
|
| 1006 |
+
"eval_runtime": 20.9058,
|
| 1007 |
+
"eval_samples_per_second": 12.341,
|
| 1008 |
+
"eval_steps_per_second": 0.861,
|
| 1009 |
+
"step": 91976
|
| 1010 |
},
|
| 1011 |
{
|
| 1012 |
+
"epoch": 4.0,
|
| 1013 |
+
"learning_rate": 2.2199027765697333e-05,
|
| 1014 |
+
"loss": 0.0019,
|
| 1015 |
+
"step": 92000
|
| 1016 |
},
|
| 1017 |
{
|
| 1018 |
+
"epoch": 4.03,
|
| 1019 |
+
"learning_rate": 2.1643327244788497e-05,
|
| 1020 |
+
"loss": 0.0015,
|
| 1021 |
+
"step": 92575
|
| 1022 |
},
|
| 1023 |
{
|
| 1024 |
+
"epoch": 4.05,
|
| 1025 |
+
"learning_rate": 2.108762672387966e-05,
|
| 1026 |
+
"loss": 0.0016,
|
| 1027 |
+
"step": 93150
|
| 1028 |
},
|
| 1029 |
{
|
| 1030 |
+
"epoch": 4.08,
|
| 1031 |
+
"learning_rate": 2.0531926202970826e-05,
|
| 1032 |
+
"loss": 0.0015,
|
| 1033 |
+
"step": 93725
|
| 1034 |
},
|
| 1035 |
{
|
| 1036 |
+
"epoch": 4.1,
|
| 1037 |
+
"learning_rate": 1.997622568206199e-05,
|
| 1038 |
+
"loss": 0.0017,
|
| 1039 |
+
"step": 94300
|
| 1040 |
},
|
| 1041 |
{
|
| 1042 |
+
"epoch": 4.13,
|
| 1043 |
+
"learning_rate": 1.942052516115315e-05,
|
| 1044 |
+
"loss": 0.0016,
|
| 1045 |
+
"step": 94875
|
| 1046 |
},
|
| 1047 |
{
|
| 1048 |
+
"epoch": 4.15,
|
| 1049 |
+
"learning_rate": 1.8864824640244315e-05,
|
| 1050 |
+
"loss": 0.0017,
|
| 1051 |
+
"step": 95450
|
| 1052 |
},
|
| 1053 |
{
|
| 1054 |
+
"epoch": 4.18,
|
| 1055 |
+
"learning_rate": 1.830912411933548e-05,
|
| 1056 |
+
"loss": 0.0017,
|
| 1057 |
+
"step": 96025
|
| 1058 |
},
|
| 1059 |
{
|
| 1060 |
+
"epoch": 4.2,
|
| 1061 |
+
"learning_rate": 1.7753423598426644e-05,
|
| 1062 |
+
"loss": 0.0015,
|
| 1063 |
+
"step": 96600
|
| 1064 |
},
|
| 1065 |
{
|
| 1066 |
+
"epoch": 4.23,
|
| 1067 |
+
"learning_rate": 1.719772307751781e-05,
|
| 1068 |
+
"loss": 0.0018,
|
| 1069 |
+
"step": 97175
|
| 1070 |
},
|
| 1071 |
{
|
| 1072 |
+
"epoch": 4.25,
|
| 1073 |
+
"learning_rate": 1.6642022556608973e-05,
|
| 1074 |
+
"loss": 0.0018,
|
| 1075 |
+
"step": 97750
|
| 1076 |
},
|
| 1077 |
{
|
| 1078 |
+
"epoch": 4.28,
|
| 1079 |
+
"learning_rate": 1.6086322035700134e-05,
|
| 1080 |
+
"loss": 0.0014,
|
| 1081 |
+
"step": 98325
|
| 1082 |
},
|
| 1083 |
{
|
| 1084 |
+
"epoch": 4.3,
|
| 1085 |
+
"learning_rate": 1.5530621514791298e-05,
|
| 1086 |
+
"loss": 0.0016,
|
| 1087 |
+
"step": 98900
|
| 1088 |
},
|
| 1089 |
{
|
| 1090 |
+
"epoch": 4.33,
|
| 1091 |
+
"learning_rate": 1.4974920993882462e-05,
|
| 1092 |
+
"loss": 0.0018,
|
| 1093 |
+
"step": 99475
|
| 1094 |
},
|
| 1095 |
{
|
| 1096 |
+
"epoch": 4.35,
|
| 1097 |
+
"learning_rate": 1.4419220472973627e-05,
|
| 1098 |
+
"loss": 0.0015,
|
| 1099 |
+
"step": 100050
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1100 |
},
|
| 1101 |
{
|
| 1102 |
+
"epoch": 4.38,
|
| 1103 |
+
"learning_rate": 1.3863519952064791e-05,
|
| 1104 |
"loss": 0.0019,
|
| 1105 |
+
"step": 100625
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1106 |
},
|
| 1107 |
{
|
| 1108 |
+
"epoch": 4.4,
|
| 1109 |
+
"learning_rate": 1.3307819431155954e-05,
|
| 1110 |
+
"loss": 0.0016,
|
| 1111 |
+
"step": 101200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1112 |
},
|
| 1113 |
{
|
| 1114 |
+
"epoch": 4.43,
|
| 1115 |
+
"learning_rate": 1.2752118910247118e-05,
|
| 1116 |
+
"loss": 0.0015,
|
| 1117 |
+
"step": 101775
|
| 1118 |
},
|
| 1119 |
{
|
| 1120 |
+
"epoch": 4.45,
|
| 1121 |
+
"learning_rate": 1.2196418389338282e-05,
|
| 1122 |
+
"loss": 0.0017,
|
| 1123 |
+
"step": 102350
|
| 1124 |
},
|
| 1125 |
{
|
| 1126 |
+
"epoch": 4.48,
|
| 1127 |
+
"learning_rate": 1.1640717868429447e-05,
|
| 1128 |
+
"loss": 0.0016,
|
| 1129 |
+
"step": 102925
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
+
"epoch": 4.5,
|
| 1133 |
+
"learning_rate": 1.108501734752061e-05,
|
| 1134 |
+
"loss": 0.0015,
|
| 1135 |
+
"step": 103500
|
| 1136 |
},
|
| 1137 |
{
|
| 1138 |
+
"epoch": 4.53,
|
| 1139 |
+
"learning_rate": 1.0529316826611774e-05,
|
| 1140 |
"loss": 0.0017,
|
| 1141 |
+
"step": 104075
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
+
"epoch": 4.55,
|
| 1145 |
+
"learning_rate": 9.973616305702938e-06,
|
| 1146 |
+
"loss": 0.0016,
|
| 1147 |
+
"step": 104650
|
| 1148 |
},
|
| 1149 |
{
|
| 1150 |
+
"epoch": 4.58,
|
| 1151 |
+
"learning_rate": 9.4179157847941e-06,
|
| 1152 |
+
"loss": 0.0016,
|
| 1153 |
+
"step": 105225
|
| 1154 |
},
|
| 1155 |
{
|
| 1156 |
+
"epoch": 4.6,
|
| 1157 |
+
"learning_rate": 8.862215263885265e-06,
|
| 1158 |
+
"loss": 0.0017,
|
| 1159 |
+
"step": 105800
|
| 1160 |
},
|
| 1161 |
{
|
| 1162 |
+
"epoch": 4.63,
|
| 1163 |
+
"learning_rate": 8.30651474297643e-06,
|
| 1164 |
+
"loss": 0.0015,
|
| 1165 |
+
"step": 106375
|
| 1166 |
},
|
| 1167 |
{
|
| 1168 |
+
"epoch": 4.65,
|
| 1169 |
+
"learning_rate": 7.750814222067592e-06,
|
| 1170 |
+
"loss": 0.0014,
|
| 1171 |
+
"step": 106950
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
+
"epoch": 4.68,
|
| 1175 |
+
"learning_rate": 7.195113701158756e-06,
|
| 1176 |
"loss": 0.0017,
|
| 1177 |
+
"step": 107525
|
| 1178 |
},
|
| 1179 |
{
|
| 1180 |
+
"epoch": 4.7,
|
| 1181 |
+
"learning_rate": 6.639413180249921e-06,
|
| 1182 |
+
"loss": 0.0017,
|
| 1183 |
+
"step": 108100
|
| 1184 |
},
|
| 1185 |
{
|
| 1186 |
+
"epoch": 4.73,
|
| 1187 |
+
"learning_rate": 6.083712659341084e-06,
|
| 1188 |
+
"loss": 0.0016,
|
| 1189 |
+
"step": 108675
|
| 1190 |
},
|
| 1191 |
{
|
| 1192 |
+
"epoch": 4.75,
|
| 1193 |
+
"learning_rate": 5.528012138432248e-06,
|
| 1194 |
"loss": 0.0017,
|
| 1195 |
+
"step": 109250
|
| 1196 |
},
|
| 1197 |
{
|
| 1198 |
+
"epoch": 4.78,
|
| 1199 |
+
"learning_rate": 4.972311617523412e-06,
|
| 1200 |
"loss": 0.0018,
|
| 1201 |
+
"step": 109825
|
| 1202 |
},
|
| 1203 |
{
|
| 1204 |
+
"epoch": 4.8,
|
| 1205 |
+
"learning_rate": 4.4166110966145756e-06,
|
| 1206 |
+
"loss": 0.0015,
|
| 1207 |
+
"step": 110400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1208 |
},
|
| 1209 |
{
|
| 1210 |
+
"epoch": 4.83,
|
| 1211 |
+
"learning_rate": 3.86091057570574e-06,
|
| 1212 |
+
"loss": 0.0017,
|
| 1213 |
+
"step": 110975
|
| 1214 |
},
|
| 1215 |
{
|
| 1216 |
+
"epoch": 4.85,
|
| 1217 |
+
"learning_rate": 3.3052100547969034e-06,
|
| 1218 |
+
"loss": 0.0014,
|
| 1219 |
+
"step": 111550
|
| 1220 |
},
|
| 1221 |
{
|
| 1222 |
+
"epoch": 4.88,
|
| 1223 |
+
"learning_rate": 2.7495095338880677e-06,
|
| 1224 |
"loss": 0.0018,
|
| 1225 |
+
"step": 112125
|
| 1226 |
},
|
| 1227 |
{
|
| 1228 |
+
"epoch": 4.9,
|
| 1229 |
+
"learning_rate": 2.1938090129792312e-06,
|
| 1230 |
"loss": 0.0017,
|
| 1231 |
+
"step": 112700
|
| 1232 |
},
|
| 1233 |
{
|
| 1234 |
+
"epoch": 4.93,
|
| 1235 |
+
"learning_rate": 1.6381084920703951e-06,
|
| 1236 |
"loss": 0.0018,
|
| 1237 |
+
"step": 113275
|
| 1238 |
},
|
| 1239 |
{
|
| 1240 |
+
"epoch": 4.95,
|
| 1241 |
+
"learning_rate": 1.082407971161559e-06,
|
| 1242 |
+
"loss": 0.0015,
|
| 1243 |
+
"step": 113850
|
| 1244 |
},
|
| 1245 |
{
|
| 1246 |
+
"epoch": 4.98,
|
| 1247 |
+
"learning_rate": 5.26707450252723e-07,
|
| 1248 |
+
"loss": 0.0016,
|
| 1249 |
+
"step": 114425
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 5.0,
|
| 1253 |
+
"eval_loss": 0.027882983908057213,
|
| 1254 |
"eval_max_distance": 8,
|
| 1255 |
"eval_mean_distance": 0,
|
| 1256 |
+
"eval_runtime": 20.563,
|
| 1257 |
+
"eval_samples_per_second": 12.547,
|
| 1258 |
+
"eval_steps_per_second": 0.875,
|
| 1259 |
+
"step": 114970
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 5.0,
|
| 1263 |
+
"step": 114970,
|
| 1264 |
+
"total_flos": 2.9139726999711744e+16,
|
| 1265 |
+
"train_loss": 0.0019824859863435676,
|
| 1266 |
+
"train_runtime": 8494.2801,
|
| 1267 |
+
"train_samples_per_second": 203.021,
|
| 1268 |
+
"train_steps_per_second": 13.535
|
| 1269 |
}
|
| 1270 |
],
|
| 1271 |
+
"logging_steps": 575,
|
| 1272 |
+
"max_steps": 114970,
|
| 1273 |
+
"num_train_epochs": 5,
|
| 1274 |
+
"save_steps": 1150,
|
| 1275 |
+
"total_flos": 2.9139726999711744e+16,
|
| 1276 |
"trial_name": null,
|
| 1277 |
"trial_params": null
|
| 1278 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4091
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8318e24b1ced526ec88f5a701462bec50052cffbe6f8dcc3d2adf56c581c256
|
| 3 |
size 4091
|